© 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. 57532
    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
    ä¼ij
    -0.25
    cerr
    -0.25
     overall
    -0.24
     down
    -0.24
    оÑĢм
    -0.24
    íľ´
    -0.24
     Sense
    -0.23
     pneumonia
    -0.23
    ain
    -0.23
    esthes
    -0.23
    POSITIVE LOGITS
     yielded
    0.28
    ä¸İä¸ŃåĽ½
    0.26
    etail
    0.26
    åij¨è½¬
    0.26
     exporter
    0.25
    ä¸İåıijå±ķ
    0.25
     Bhar
    0.25
    consistent
    0.25
     trustworthy
    0.24
     linker
    0.24
    Activations Density 0.086%

    No Known Activations

    This feature has no known activations.