© 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. 8688
    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
    èıģ
    -0.35
    个å°ıæŶ
    -0.31
    (rest
    -0.28
     overlooking
    -0.27
     spor
    -0.25
    >[]
    -0.24
    toFixed
    -0.24
    Reducers
    -0.24
    restore
    -0.24
    rest
    -0.23
    POSITIVE LOGITS
    lider
    0.29
    Foreign
    0.28
    _END
    0.28
     (::
    0.27
     Foreign
    0.27
    atform
    0.27
    ä¸ĢåŃĹ
    0.26
    æľ«
    0.25
    ä¸įéĢĤ
    0.25
    è¿Ļå¼ł
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.