© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22300
    Prev
    Next
    INDEX
    Explanations

    equivalent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩĩæļĸ
    -0.28
    æĸ°å¹´
    -0.25
    иÑĢовка
    -0.25
    ema
    -0.24
    ä¾Ľæļĸ
    -0.24
    ","",
    -0.24
    ä¸īæĿ¡
    -0.24
    avl
    -0.24
    份
    -0.24
    æĺ¥è¿IJ
    -0.23
    POSITIVE LOGITS
    PEED
    0.25
    jing
    0.24
    igu
    0.24
    æŁĶ
    0.23
    _DEPRECATED
    0.23
     memorial
    0.23
    OrCreate
    0.23
    身å¿ĥåģ¥åº·
    0.23
    _DUMP
    0.23
    .si
    0.23
    Activations Density 0.068%

    No Known Activations