© 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. 57620
    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
    æĪĺæĸĹ
    -0.25
    asaki
    -0.25
    WARE
    -0.25
    alli
    -0.25
     ware
    -0.25
    æĢĢæĬ±
    -0.24
    桶
    -0.24
    arkin
    -0.24
    oman
    -0.24
    åºĵéĩĮ
    -0.23
    POSITIVE LOGITS
    éĢĨè¡Į
    0.26
    å¹´ä¹ĭ
    0.25
    æŃ¥æŃ¥
    0.23
     accr
    0.23
     turnaround
    0.23
    çĻ»å±±
    0.23
     (:
    0.23
    icon
    0.23
     instant
    0.23
    PEND
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.