© 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. 90232
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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
     provisions
    -0.27
    å¥Ħ
    -0.27
    ittle
    -0.27
    ilinear
    -0.26
    mani
    -0.26
    éŁ©åĽ½
    -0.26
     Heard
    -0.25
    pell
    -0.25
     provisional
    -0.24
    edriver
    -0.24
    POSITIVE LOGITS
    å·¥ä½ľèĢħ
    0.26
    èĵī
    0.26
    èĿ¶
    0.26
    criptors
    0.25
    èĢģå¸Ī
    0.24
    念
    0.24
    éĿ¢åIJij
    0.24
     Staff
    0.24
    æĵİ
    0.24
    omics
    0.24
    Activations Density 3.461%

    No Known Activations