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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85166
    Prev
    Next
    INDEX
    Explanations

    ucch

    np_max-act · gemini-2.0-flash

    tokens containing the character sequence "ucch" (a substring that often appears in Italian surnames).

    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
    ‚
    -0.08
    有一
    -0.07
     Nil
    -0.07
     MN
    -0.07
    alin
    -0.07
    뗏
    -0.07
    孑
    -0.07
    无
    -0.07
     mining
    -0.07
    Guardar
    -0.07
    POSITIVE LOGITS
     конструк
    0.07
    个交易
    0.07
    mailto
    0.07
     dbHelper
    0.07
    𓃢
    0.07
    أمراض
    0.07
     diplom
    0.07
     People
    0.07
     актуальн
    0.07
    оборот
    0.07
    Activations Density 0.280%

    No Known Activations