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. 1678
    Prev
    Next
    INDEX
    Explanations

    code and database queries

    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
    аÑĢам
    -0.28
     rain
    -0.27
    lescope
    -0.26
    çĹĴ
    -0.26
     Wimbledon
    -0.26
    ikki
    -0.26
    belief
    -0.25
    isque
    -0.25
    inati
    -0.25
    atables
    -0.24
    POSITIVE LOGITS
     pp
    0.26
    èįī
    0.26
    (pp
    0.26
    addComponent
    0.25
    =Math
    0.24
    äºĺ
    0.24
     categorized
    0.24
     viewed
    0.24
     prag
    0.24
    åģľä¸ĭæĿ¥
    0.23
    Activations Density 0.007%

    No Known Activations