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

    Neuronpedia

    APICircuit 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. 6976
    Prev
    Next
    INDEX
    Explanations

    District

    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
    相应的
    -0.08
    类
    -0.08
    ሓ
    -0.07
    /comment
    -0.07
    撥
    -0.07
    _ar
    -0.07
    㳬
    -0.07
     given
    -0.07
     categories
    -0.07
    ther
    -0.07
    POSITIVE LOGITS
    颜值
    0.08
     диз
    0.08
     rims
    0.07
    芝加
    0.07
     بدون
    0.07
    娵
    0.07
    具有战士
    0.07
     distra
    0.07
     countert
    0.07
     Clients
    0.07
    Activations Density 0.001%

    No Known Activations