© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 2111
    Prev
    Next
    INDEX
    Explanations

    Internet texts

    np_max-act · gemini-2.0-flash

    tokens that mark dates, times, section headings or other numeric/metadata elements (numbers, years, timestamps, and similar header-like tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    孔雀
    -0.07
     Title
    -0.07
     extend
    -0.07
    债权
    -0.07
    鲇
    -0.07
    商铺
    -0.06
     Reign
    -0.06
    itrust
    -0.06
     التداول
    -0.06
    行走
    -0.06
    POSITIVE LOGITS
     laisse
    0.07
    resentation
    0.07
     mutableListOf
    0.07
     Fran
    0.07
    rocess
    0.06
     consisted
    0.06
    _categories
    0.06
    .cleaned
    0.06
     Claus
    0.06
     linestyle
    0.06
    Activations Density 0.243%

    No Known Activations