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. 36400
    Prev
    Next
    INDEX
    Explanations

    1

    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
     bulk
    -0.07
    %C
    -0.07
    バン
    -0.07
    法律责任
    -0.07
    很多人
    -0.07
    魔鬼
    -0.07
     calm
    -0.07
    \xc
    -0.06
    拂
    -0.06
    %c
    -0.06
    POSITIVE LOGITS
    互通
    0.08
    platform
    0.08
    завис
    0.07
     homem
    0.07
    停车位
    0.07
    加盟商
    0.07
     nem
    0.06
     Bridges
    0.06
    放假
    0.06
    基站
    0.06
    Activations Density 0.001%

    No Known Activations