© 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. 56992
    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
    ScreenWidth
    -0.25
    opoulos
    -0.25
    icum
    -0.24
    éĢ²ä¸ĢæŃ¥
    -0.24
    è¿Ľä¸ĢæŃ¥
    -0.24
    æ¿Ĥ
    -0.24
    åĨķ
    -0.24
    FPS
    -0.24
    .Refresh
    -0.23
     pitched
    -0.23
    POSITIVE LOGITS
    .getLog
    0.27
    ắc
    0.26
    AME
    0.26
    ame
    0.25
    noun
    0.25
    OrElse
    0.24
    prepend
    0.24
    (import
    0.24
    воÑĢоÑĤ
    0.24
    (dot
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.