© 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. 130021
    Prev
    Next
    INDEX
    Explanations

    quotations, patients

    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
     ?");↵
    -0.28
    tones
    -0.27
    ừa
    -0.27
    -strokes
    -0.25
    ynes
    -0.25
    å§ĵ
    -0.25
     columnHeader
    -0.25
    ariate
    -0.24
     Downs
    -0.24
    ownik
    -0.24
    POSITIVE LOGITS
    d
    0.32
    æĬ½
    0.30
    .
    0.28
    rou
    0.28
     group
    0.27
    4
    0.27
    k
    0.27
    6
    0.27
     draw
    0.27
    B
    0.26
    Activations Density 9.695%

    No Known Activations