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. 11-TRANSCODER-HP
    4. 46425
    Prev
    Next
    INDEX
    Explanations

    Team-building or currency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bear
    -0.28
    ä»ĭç»į
    -0.26
    ...'↵
    -0.26
     ger
    -0.26
    åĩºè·¯
    -0.25
    IRT
    -0.25
    alties
    -0.24
     mont
    -0.24
     bear
    -0.24
    aget
    -0.24
    POSITIVE LOGITS
    åĬŀ好
    0.27
     używa
    0.27
     Bd
    0.25
    -version
    0.25
    å¨ģèĥģ
    0.25
    Piece
    0.24
    é¢ģ
    0.24
    _emit
    0.23
    roat
    0.23
    å¸ľ
    0.23
    Activations Density 0.056%

    No Known Activations