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. 41233
    Prev
    Next
    INDEX
    Explanations

    Estonia

    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
    ar
    -0.07
    ứng
    -0.07
    jar
    -0.07
    斗
    -0.07
     cảm
    -0.07
    red
    -0.07
     hid
    -0.07
    🎲
    -0.07
    ﺋ
    -0.07
    Illegal
    -0.06
    POSITIVE LOGITS
     pertaining
    0.08
     posterior
    0.08
    🆖
    0.07
    _answer
    0.07
     elek
    0.07
    骶
    0.07
    process
    0.07
    :@"%@
    0.07
     Nielsen
    0.07
    ✾
    0.06
    Activations Density 0.001%

    No Known Activations