© 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. 22185
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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
    Negative Logits
    egr
    -0.28
    çĻľ
    -0.27
    磨
    -0.27
    egra
    -0.25
     geb
    -0.25
    ä¾Ħ
    -0.25
     individually
    -0.24
    ledger
    -0.24
    è¢ĭ
    -0.24
     Winn
    -0.24
    POSITIVE LOGITS
    __.__
    0.31
    zym
    0.29
    åħ°èĬ±
    0.29
    转移åĪ°
    0.28
    ä»Ħ
    0.28
    æĸ°éĻĪ代谢
    0.27
    oS
    0.27
    éĵ±
    0.26
    casting
    0.25
    幸
    0.25
    Activations Density 0.001%

    No Known Activations