© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 106888
    Prev
    Next
    INDEX
    Explanations

    technical publications

    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
     Lose
    -0.25
    éĻį温
    -0.24
    -edge
    -0.24
    -ce
    -0.24
    [arg
    -0.24
    inator
    -0.23
    æĢİèĥ½
    -0.23
    inkle
    -0.23
     Äijá»ķi
    -0.22
    qn
    -0.22
    POSITIVE LOGITS
    ams
    0.29
     pump
    0.26
    :checked
    0.25
    缸åIJĮçļĦ
    0.25
    %S
    0.25
    ä¹ĭåĬ¿
    0.25
     Gratis
    0.24
     prank
    0.24
    pper
    0.24
     morning
    0.24
    Activations Density 11.449%

    No Known Activations