© 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. 141595
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    idal
    -0.28
    vos
    -0.27
    hab
    -0.26
    éĩİ
    -0.26
    Pred
    -0.26
    _PRED
    -0.26
    ç²Ł
    -0.25
     dorm
    -0.25
     maxim
    -0.25
    alin
    -0.25
    POSITIVE LOGITS
    æļ´éĽ¨
    0.26
    åĨ²éĶĭ
    0.26
    upy
    0.26
     elbows
    0.25
    reat
    0.24
    ungs
    0.24
    (br
    0.23
    }px
    0.23
    confirm
    0.23
    è¿ĩåī©
    0.23
    Activations Density 91.221%

    No Known Activations

    This feature has no known activations.