© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4805
    Prev
    Next
    INDEX
    Explanations

    Code and web pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åį´è¢«
    -0.28
    çŁ¥åIJį度
    -0.27
    omore
    -0.27
    已被
    -0.27
    _exc
    -0.27
    åħ¬çĽĬæĢ§
    -0.26
    çıįè´µ
    -0.25
    #
    -0.25
     tearDown
    -0.25
    æīįæĺ¯çľŁæŃ£
    -0.25
    POSITIVE LOGITS
    æľīä¸įåIJĮçļĦ
    0.30
     frat
    0.28
     determined
    0.28
     clockwise
    0.27
    rous
    0.26
    æīģ
    0.25
    ä¸įåIJĮçļĦ
    0.25
    ÑĢаÐ
    0.25
    riet
    0.25
    åIJĦè¡Į
    0.25
    Activations Density 0.002%

    No Known Activations