© 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. 24-TRANSCODER-HP
    7. 150315
    Prev
    Next
    INDEX
    Explanations

    rules and requirements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocalyptic
    -0.25
    ergy
    -0.25
    ippo
    -0.24
    pressive
    -0.24
    çªĴ
    -0.24
    ä¼¼çļĦ
    -0.23
    祺
    -0.23
    .quit
    -0.23
    çĿ¹
    -0.23
    CellValue
    -0.23
    POSITIVE LOGITS
    åIJĥ
    0.27
     kto
    0.27
    èĪĨ
    0.27
    æĺ¯éŁ©åĽ½
    0.27
    -util
    0.25
    wil
    0.25
    èģ¯
    0.25
    èªįãĤģ
    0.25
    åħģ许
    0.25
    çĪ¸çĪ¸
    0.25
    Activations Density 0.112%

    No Known Activations