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. 146615
    Prev
    Next
    INDEX
    Explanations

    of

    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
    [['
    -0.25
     dose
    -0.25
    確å®ļ
    -0.24
    ç§»æ¤į
    -0.24
    ç¡®å®ļ
    -0.24
     trail
    -0.24
    Accent
    -0.24
     невоз
    -0.24
    /catalog
    -0.24
    ä¸įåı¯èĥ½
    -0.23
    POSITIVE LOGITS
    æĬķ
    0.33
    ç»ĵ
    0.32
    /weather
    0.28
    /body
    0.28
    dings
    0.28
    SX
    0.28
    stag
    0.26
    论åĿĽ
    0.25
    çķĻ
    0.25
    æĭĽèģĺ
    0.25
    Activations Density 0.065%

    No Known Activations