© 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. 29878
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    使åij½
    -0.31
    管çIJĨæĿ¡ä¾ĭ
    -0.28
     conven
    -0.27
    ç¼IJ
    -0.25
     обÑĬ
    -0.24
    Dou
    -0.24
    线ä¸Ĭ
    -0.24
     Dawson
    -0.23
    oleans
    -0.23
    eman
    -0.23
    POSITIVE LOGITS
    refs
    0.26
     refs
    0.25
    å±ĭåŃIJ
    0.25
    èĢĥè¯ģ
    0.25
    ä¸įç»ı
    0.24
    åİ¢
    0.24
    äºĨ好åĩł
    0.24
    {*
    0.24
     contributed
    0.23
     iss
    0.23
    Activations Density 9.534%

    No Known Activations