© 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. 30-TRANSCODER-HP
    7. 95975
    Prev
    Next
    INDEX
    Explanations

    Washington State

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cor
    -0.34
     OR
    -0.30
     scalar
    -0.29
    scalar
    -0.28
    avy
    -0.26
     Ore
    -0.26
    óg
    -0.26
    çĶ¨æĪ·æıIJä¾Ľ
    -0.25
    sheet
    -0.25
    æĿ²
    -0.25
    POSITIVE LOGITS
     Seahawks
    0.30
     Sound
    0.29
    åįİçĽĽé¡¿
    0.29
     King
    0.27
     KING
    0.27
    æ²¥
    0.27
     Spokane
    0.27
     Sno
    0.27
     Mercer
    0.26
     Seattle
    0.25
    Activations Density 1.097%

    No Known Activations