© 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. 9440
    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
    lest
    -0.26
    ®
    -0.26
    å®Įåħ¨
    -0.26
    æĻ¦
    -0.25
     Gle
    -0.25
    glomer
    -0.24
     cit
    -0.24
    å®Įæķ´
    -0.24
    æĺ¾
    -0.24
     hybrid
    -0.24
    POSITIVE LOGITS
    ady
    0.27
    æĪIJ为ä¸ŃåĽ½
    0.26
    ince
    0.26
    Invariant
    0.26
    ADX
    0.25
     Lone
    0.25
     createAction
    0.24
    æĸĩä½ĵ
    0.24
    (choices
    0.24
     extr
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.