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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30014
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    离
    -0.27
    ধ
    -0.26
    ipro
    -0.26
    åħ¢
    -0.26
     prog
    -0.25
    æ³µ
    -0.24
    @student
    -0.24
    èĥį
    -0.24
     UIApplication
    -0.24
    @[
    -0.24
    POSITIVE LOGITS
     echoed
    0.26
    å¹¼
    0.26
    ously
    0.26
    工人
    0.25
     Sadd
    0.25
    ä¸įåIJĮç¨ĭ度
    0.25
    éķĤ
    0.25
    -thumbnails
    0.24
    _tickets
    0.24
    ç¢Ł
    0.24
    Activations Density 1.193%

    No Known Activations