© 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. 20-TRANSCODER-HP
    7. 131009
    Prev
    Next
    INDEX
    Explanations

    descriptive/scientific language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    otics
    -0.29
    éĢģåĩº
    -0.28
    åŁł
    -0.25
    åĬłçĽĸ
    -0.25
    ics
    -0.25
    ×ķתר
    -0.25
    åı°éĺ¶
    -0.24
    @stop
    -0.24
    èĭ«
    -0.24
    ICS
    -0.23
    POSITIVE LOGITS
    款
    0.31
    ä¸Ģ款
    0.27
    Uint
    0.26
    åĪģ
    0.26
    cion
    0.26
    ilon
    0.25
    éĵģ
    0.25
    åĩłä¸ª
    0.24
     gal
    0.24
     tanto
    0.24
    Activations Density 2.993%

    No Known Activations