© 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. 8986
    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
     join
    -0.28
    /copyleft
    -0.28
    æĸ¹ä¾¿
    -0.26
    èĢĮæĿ¥
    -0.24
    å½±
    -0.24
    eca
    -0.24
    ä¸Ģ人
    -0.24
    IDEO
    -0.23
    .join
    -0.23
    _scheme
    -0.23
    POSITIVE LOGITS
    è²Ĥ
    0.28
    enser
    0.28
    ¶Ī
    0.28
    /out
    0.28
    offsetof
    0.26
    å¿Ĺ强
    0.25
    æݺ
    0.24
    .Does
    0.24
    dorf
    0.24
    é¦ĸå¯Į
    0.24
    Activations Density 0.888%

    No Known Activations

    This feature has no known activations.