© 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. 112356
    Prev
    Next
    INDEX
    Explanations

    participation, involvement

    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
     contr
    -0.29
    ä¼ģ
    -0.26
    æķĸ
    -0.26
    iken
    -0.25
    é¢ī
    -0.25
     blaze
    -0.25
    inos
    -0.25
    <iostream
    -0.24
    å°¾
    -0.24
     templ
    -0.23
    POSITIVE LOGITS
     reached
    0.27
    è§Ĵ度æĿ¥çľĭ
    0.25
    éģİç¨ĭä¸Ń
    0.25
     reaching
    0.24
    atch
    0.24
    è¾¾åĪ°äºĨ
    0.23
    æĥħåĨµæĿ¥çľĭ
    0.23
    綦
    0.23
     reaches
    0.23
    achs
    0.23
    Activations Density 0.045%

    No Known Activations