© 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. 63653
    Prev
    Next
    INDEX
    Explanations

    organizations, rules, and events

    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
    alue
    -0.28
     Study
    -0.28
    =color
    -0.27
    è´ŁéĿ¢å½±åĵį
    -0.27
    mith
    -0.26
     slots
    -0.26
    agh
    -0.26
     study
    -0.25
    slots
    -0.25
    误ä¼ļ
    -0.25
    POSITIVE LOGITS
     overriding
    0.27
    getc
    0.27
    extends
    0.26
    èµ·çłģ
    0.25
    Ļ¨
    0.25
    ipel
    0.25
     intervening
    0.24
    .offsetTop
    0.24
    ä¸ĭä¸Ģ
    0.24
    åľ¨éĤ£éĩĮ
    0.24
    Activations Density 28.127%

    No Known Activations