© 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. 15-RESID-POST-AA
    11. 30658
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جهاد
    -0.07
    uai
    -0.07
    ów
    -0.07
     indulge
    -0.07
    amax
    -0.07
    خدم
    -0.07
    들을
    -0.06
    皇宫
    -0.06
     pleading
    -0.06
    .data
    -0.06
    POSITIVE LOGITS
    在整个
    0.08
    _nombre
    0.08
    Returns
    0.07
     Notre
    0.07
    -trigger
    0.07
    .Dis
    0.07
    ʁ
    0.07
     الخارج
    0.07
     TORT
    0.06
     artifact
    0.06
    Activations Density 0.024%

    No Known Activations