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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 109979
    Prev
    Next
    INDEX
    Explanations

    plants and trees

    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
    ᐊ
    -0.07
    ຄ
    -0.07
    ullan
    -0.07
    vé
    -0.07
     Rockefeller
    -0.07
    /tiny
    -0.07
     kích
    -0.06
     topo
    -0.06
     yaşında
    -0.06
    被执行人
    -0.06
    POSITIVE LOGITS
    AIL
    0.07
    Leg
    0.07
    _res
    0.07
    reeting
    0.06
    client
    0.06
    аем
    0.06
     الشر
    0.06
     пу
    0.06
    蓉
    0.06
    dif
    0.06
    Activations Density 0.017%

    No Known Activations