© 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. 18-TRANSCODER-HP
    7. 90236
    Prev
    Next
    INDEX
    Explanations

    compete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    段
    -0.26
    ðŁij¤
    -0.25
    ewise
    -0.25
     FAST
    -0.24
     tapes
    -0.23
    _quant
    -0.23
    ä¸įåĩºæĿ¥
    -0.23
    è¿ĻåIJį
    -0.23
    ey
    -0.23
    æĶ¾æĿ¾
    -0.23
    POSITIVE LOGITS
    .Annotations
    0.28
    æ³ķå¾ĭè§Ħå®ļ
    0.26
     Disorder
    0.26
    çĸ½
    0.26
    主è¦ģåĨħ容
    0.26
    ModelError
    0.25
    ä¸Ģèĩ´
    0.25
    Launch
    0.24
    Sharp
    0.24
    åįŀ
    0.24
    Activations Density 13.104%

    No Known Activations