© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9567
    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
    纸ä¸Ĭ
    -0.25
    å¤ļä¸ĩ
    -0.24
    DBG
    -0.24
    Works
    -0.24
     universal
    -0.24
     stripslashes
    -0.24
    _UNDER
    -0.23
     fortn
    -0.23
     prer
    -0.23
    ~↵↵
    -0.23
    POSITIVE LOGITS
    åķ¸
    0.25
     Catch
    0.24
    ICLE
    0.24
    inue
    0.23
    ingle
    0.23
    æĶ¶çº³
    0.23
    .override
    0.23
    ä¸ŃåĽ½åĽ½éĻħ
    0.23
    .Schedule
    0.23
    illian
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.