© 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. 8359
    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
    ä½ľèĢħæľ¬äºº
    -0.26
    arge
    -0.26
    ãģıãĤĮ
    -0.25
     CALLBACK
    -0.25
    distribution
    -0.24
    UGH
    -0.24
    å®īçĦ¶
    -0.23
    ppe
    -0.23
    æµģè¡Į
    -0.23
    /share
    -0.23
    POSITIVE LOGITS
    ings
    0.27
    wig
    0.25
     distinguished
    0.25
    游æĪı
    0.25
    æĶ¿åºľ
    0.25
     juego
    0.25
    INGS
    0.24
     game
    0.24
    apan
    0.24
     attract
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.