© 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. 19-RESID-POST-AA
    11. 8108
    Prev
    Next
    INDEX
    Explanations

    flattening shapes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çocuklar
    -0.08
    💊
    -0.07
    钘
    -0.07
    ũng
    -0.07
     الصحة
    -0.07
    奶粉
    -0.07
     cảnh
    -0.07
     molec
    -0.07
     segurança
    -0.07
    مساعدة
    -0.07
    POSITIVE LOGITS
    ﾛ
    0.08
    に向
    0.07
     Plants
    0.07
     rejo
    0.07
     forty
    0.07
    noxious
    0.07
    —we
    0.07
    Redirect
    0.07
    ７
    0.06
    剁
    0.06
    Activations Density 0.001%

    No Known Activations