© 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. 9-TRANSCODER-HP
    7. 29153
    Prev
    Next
    INDEX
    Explanations

    inf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÃŃst
    -0.26
    =((
    -0.25
    åĪĨæīĭ
    -0.25
    getWindow
    -0.24
    åijĬè¯ī
    -0.24
     Slice
    -0.24
    åī²
    -0.24
    æľ¬åľ°
    -0.23
    åįĥ
    -0.23
     här
    -0.23
    POSITIVE LOGITS
     traveler
    0.25
    çľł
    0.24
    åĬ³ç´¯
    0.24
     Khal
    0.24
    StrictEqual
    0.24
     Ort
    0.24
    eneg
    0.24
     bland
    0.23
    èĦĴ
    0.23
     prejudice
    0.23
    Activations Density 0.817%

    No Known Activations