© 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. 27-TRANSCODER-HP
    7. 57991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opp
    -0.27
    èĢ³
    -0.27
    ymbols
    -0.26
    为客æĪ·
    -0.26
    iro
    -0.26
     CY
    -0.25
    elier
    -0.24
    å¾Ģè¿Ķ
    -0.24
    çļĦæ¶Īæģ¯
    -0.24
    (Op
    -0.24
    POSITIVE LOGITS
    ologi
    0.28
     theological
    0.26
    andin
    0.26
    罨
    0.25
    æ¯ıå¹´éĥ½
    0.25
    cell
    0.24
    èĩ³æĸ¼
    0.24
    èĩ³äºİ
    0.24
    killer
    0.23
    ulist
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.