© 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. 107517
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    .Here
    -0.27
    pane
    -0.27
     Pane
    -0.27
    çİ·
    -0.25
     themselves
    -0.25
    ASI
    -0.25
    prove
    -0.24
     mistress
    -0.24
    edores
    -0.24
    asi
    -0.24
    POSITIVE LOGITS
    diet
    0.27
    ((*
    0.26
    .contents
    0.26
    -he
    0.25
    ))*(
    0.25
    rops
    0.25
    èĭ±
    0.24
    åı¯ä»¥èİ·å¾Ĺ
    0.23
     ${(
    0.23
    ocop
    0.23
    Activations Density 16.055%

    No Known Activations