© 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. 130446
    Prev
    Next
    INDEX
    Explanations

    Addresses and licensing information

    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
    /manage
    -0.26
    _NT
    -0.25
     заÑĤ
    -0.24
    Won
    -0.23
    å°¤åħ¶
    -0.23
     Vi
    -0.23
    å¾Ī好
    -0.23
    ç¾Ĭæ¯Ľ
    -0.23
    èĥĮéĿ¢
    -0.23
    Vi
    -0.23
    POSITIVE LOGITS
    è¨Ģ
    0.28
    çļĦä¸Ģåijĺ
    0.27
     bids
    0.26
    uplicates
    0.25
     belonging
    0.24
    çķĻ
    0.24
    çŁŃæļĤ
    0.24
    memcmp
    0.24
     cocci
    0.23
    ä¸ªé¡¹çĽ®
    0.23
    Activations Density 0.112%

    No Known Activations