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. 72229
    Prev
    Next
    INDEX
    Explanations

    sentence starts/prompts/titles

    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
    nez
    -0.29
     gross
    -0.27
    .structure
    -0.26
     simplex
    -0.26
    æ¢Ĺ
    -0.25
    åijĹ
    -0.25
    åıªèĥ½è¯´
    -0.25
    æ²³æµģ
    -0.24
    loth
    -0.24
    ä¸ĭè¡Į
    -0.24
    POSITIVE LOGITS
    adies
    0.30
    otherwise
    0.28
    Otherwise
    0.26
    lush
    0.26
    advance
    0.25
    ilitating
    0.24
     otherwise
    0.24
    fried
    0.24
    Blocking
    0.24
     advoc
    0.23
    Activations Density 0.000%

    No Known Activations