© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141136
    Prev
    Next
    INDEX
    Explanations

    versions and modifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (IO
    -0.32
     Fin
    -0.26
    zure
    -0.26
    åĨµ
    -0.26
     atleast
    -0.25
    -temp
    -0.24
    represented
    -0.24
    æ¶ī
    -0.23
    ¢åįķ
    -0.23
    ecess
    -0.23
    POSITIVE LOGITS
    æİ¥åħ¥
    0.25
    转
    0.25
     mấy
    0.24
    ä¸ī项
    0.24
    éķ¿çŁŃ
    0.24
    -secret
    0.24
     exclusion
    0.23
    æľĿ
    0.23
    _stamp
    0.23
    客è¿IJ
    0.23
    Activations Density 21.518%

    No Known Activations