© 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. 108427
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    eed
    -0.25
    heet
    -0.24
     Fut
    -0.24
    CKER
    -0.24
    [value
    -0.24
    è¦ģèĢĥèĻij
    -0.24
    è´¨åľ°
    -0.23
    _tool
    -0.23
     Ter
    -0.23
    UC
    -0.23
    POSITIVE LOGITS
    hani
    0.29
     thumb
    0.28
     fluids
    0.27
    !")
    0.27
    !!)↵
    0.26
    ”)
    0.25
    ’)
    0.24
     zak
    0.24
    pute
    0.24
    **)
    0.24
    Activations Density 22.398%

    No Known Activations