© 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. 107431
    Prev
    Next
    INDEX
    Explanations

    Engineering

    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
    iants
    -0.26
    ush
    -0.25
    ä¹ĭ称
    -0.24
    大夫
    -0.24
    gest
    -0.23
    ritz
    -0.23
    &p
    -0.23
    inya
    -0.23
    çĤĬ
    -0.23
    [this
    -0.23
    POSITIVE LOGITS
     Lyons
    0.30
    è¿ŀèĥľ
    0.28
     colon
    0.26
    zos
    0.26
    帧
    0.26
     cham
    0.25
     ring
    0.25
    æ®ĸæ°ij
    0.25
     ":
    0.24
     rematch
    0.24
    Activations Density 21.157%

    No Known Activations