© 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. 20-TRANSCODER-HP
    7. 108352
    Prev
    Next
    INDEX
    Explanations

    ility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    社ä¼ļåıijå±ķ
    -0.28
    ëĥIJ
    -0.27
     <<=
    -0.24
    lic
    -0.24
     Withdraw
    -0.24
    æ¢Ń
    -0.23
    让çĶ¨æĪ·
    -0.23
    à°¦
    -0.23
    åŁ
    -0.23
    å°±ç»Ļ大家
    -0.23
    POSITIVE LOGITS
    sterol
    0.26
    sville
    0.25
     ideally
    0.25
    otle
    0.24
    óÅĤ
    0.24
    ä¼Ĭæĸ¯
    0.24
     meanwhile
    0.23
    èĩªå·±
    0.23
     oneself
    0.23
    æ·Į
    0.23
    Activations Density 75.665%

    No Known Activations