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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 7-TRANSCODER-HP
    4. 24107
    Prev
    Next
    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ¨ä»½
    -0.25
    oser
    -0.25
     ?:
    -0.25
    éĥ¨åī¯
    -0.24
     spokeswoman
    -0.24
     GTX
    -0.24
    è£½ä½ľ
    -0.23
     whichever
    -0.23
     Cer
    -0.23
    ********************************************************
    -0.23
    POSITIVE LOGITS
    rome
    0.29
    寡
    0.28
    ksam
    0.27
    alendar
    0.26
    ä¿¡æģ¯åıijå¸ĥ
    0.26
    ABL
    0.25
    hausen
    0.25
    xm
    0.24
    ç´§è·Ł
    0.24
     Follow
    0.24
    Activations Density 0.003%

    No Known Activations