© 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. 22-TRANSCODER-HP
    7. 88261
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivation
    -0.28
    åºĵéĩĮ
    -0.27
    ä¸Ģ度
    -0.25
    å¾ĴæŃ¥
    -0.25
    idi
    -0.25
    éģĹ
    -0.24
    iez
    -0.24
    rine
    -0.24
    getPlayer
    -0.24
    .pp
    -0.24
    POSITIVE LOGITS
     future
    0.32
    éļıçĿĢæŶéĹ´
    0.28
     evolutionary
    0.28
    ocy
    0.26
    ardo
    0.25
    æľªæĿ¥çļĦ
    0.25
    åŃIJåŃĻ
    0.25
    ä»ĬåIJİ
    0.25
     our
    0.25
    entina
    0.25
    Activations Density 0.004%

    No Known Activations