© 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. 129578
    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
    enson
    -0.26
    liness
    -0.23
    äh
    -0.23
    rais
    -0.23
     curs
    -0.22
    线
    -0.22
     incentiv
    -0.22
     eag
    -0.22
    /gen
    -0.22
     account
    -0.21
    POSITIVE LOGITS
    éĤķ
    0.25
    utr
    0.24
    )::
    0.24
    _recovery
    0.23
    utes
    0.22
    nge
    0.22
    UTES
    0.22
     scrambling
    0.22
    姥
    0.21
    wap
    0.21
    Activations Density 31.244%

    No Known Activations

    This feature has no known activations.