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. 1631
    Prev
    Next
    INDEX
    Explanations

    am

    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
    åİŁåĽł
    -0.28
    ç¼ĺ
    -0.28
    -tool
    -0.27
    çļĦäºĭæĥħ
    -0.27
     Participation
    -0.26
    tal
    -0.26
    Less
    -0.26
     amp
    -0.26
     sett
    -0.25
     richest
    -0.25
    POSITIVE LOGITS
    ibilit
    0.28
    æ§ģ
    0.26
    esthes
    0.26
    rette
    0.26
    allo
    0.26
    ansas
    0.25
    osas
    0.25
    itals
    0.24
     Highlands
    0.24
    åĨ±
    0.24
    Activations Density 0.003%

    No Known Activations