© 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. 150317
    Prev
    Next
    INDEX
    Explanations

    code and foreign languages

    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
     Rosenstein
    -0.27
    çĿĢä»ĸ
    -0.27
     Background
    -0.27
     Forest
    -0.27
    foreground
    -0.26
    好æ¶Īæģ¯
    -0.26
    -lock
    -0.26
    setMessage
    -0.25
    论
    -0.25
     background
    -0.25
    POSITIVE LOGITS
    继
    0.27
    æĪ¡
    0.27
    ç¹¼
    0.26
     Scoped
    0.25
    führt
    0.25
     Klo
    0.25
    vier
    0.24
    ither
    0.24
    pha
    0.23
    alta
    0.23
    Activations Density 0.299%

    No Known Activations