© 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. 9371
    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
    nish
    -0.26
    âĢ¢↵↵
    -0.26
    产åѦ
    -0.25
    æŁ¥çľĭåħ¨æĸĩ
    -0.24
     Done
    -0.24
    .Done
    -0.24
    imitive
    -0.24
    èĤ¡
    -0.23
     Strong
    -0.23
     tweet
    -0.23
    POSITIVE LOGITS
    -INF
    0.31
    æ²ĵ
    0.27
    oba
    0.25
     huis
    0.25
    让
    0.24
    oidal
    0.24
    ä¸Ģä¸ĭ
    0.24
    çĶ¨æĿ¥
    0.23
    åį¡æĭī
    0.23
     BAT
    0.23
    Activations Density 0.132%

    No Known Activations

    This feature has no known activations.