Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92252
    Prev
    Next
    INDEX
    Explanations

    abbreviations and other languages

    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_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
     أصحاب
    -0.07
    umbo
    -0.07
     My
    -0.06
    ("\
    -0.06
    fuscated
    -0.06
    Mis
    -0.06
     mushroom
    -0.06
    imulation
    -0.06
    市
    -0.06
    {-
    -0.06
    POSITIVE LOGITS
    を入れ
    0.08
     intake
    0.07
    扭矩
    0.07
    Курс
    0.07
     الدفاع
    0.07
     kissed
    0.07
     nom
    0.07
    _general
    0.07
    背叛
    0.06
    ########################################################
    0.06
    Activations Density 0.033%

    No Known Activations