© 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. 141516
    Prev
    Next
    INDEX
    Explanations

    Structured activities/organizations

    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
    ä¸Ĭ游
    -0.32
    èij£äºĭä¼ļ
    -0.28
    å·¥ç¨ĭæĸ½å·¥
    -0.26
    ippy
    -0.26
    çļĦåį°è±¡
    -0.26
    èĥĮåIJİ
    -0.25
    arked
    -0.25
    âĵĴ
    -0.25
    .toolbar
    -0.25
     reasoning
    -0.24
    POSITIVE LOGITS
    CPF
    0.29
    ìľ¡
    0.27
    wine
    0.26
    ilian
    0.25
    ATE
    0.25
     prom
    0.25
     lim
    0.25
    åıĪèĥ½
    0.25
    unas
    0.25
     Christoph
    0.25
    Activations Density 4.263%

    No Known Activations