© 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. 9096
    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
    æijĩ
    -0.29
    view
    -0.28
     appeal
    -0.27
     appeals
    -0.27
    repr
    -0.27
    anks
    -0.27
    rex
    -0.27
    å½ĵå¹´
    -0.27
    èĻ±
    -0.25
    _FRONT
    -0.24
    POSITIVE LOGITS
     Downs
    0.31
    ripe
    0.28
    aru
    0.28
     downs
    0.27
    bz
    0.27
    atus
    0.27
    $log
    0.26
    itter
    0.26
    "f
    0.26
    arak
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.