© 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. 7657
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    ä¸į平衡
    -0.28
     tow
    -0.25
    _STEP
    -0.25
     thanking
    -0.24
    (SK
    -0.23
    _sk
    -0.23
     Sanford
    -0.23
    çIJĨæĥ³çļĦ
    -0.23
    çĶ¨æĿ¥
    -0.23
    orary
    -0.23
    POSITIVE LOGITS
    åĮ£
    0.28
    modx
    0.25
    odic
    0.24
    嬴
    0.24
    ucer
    0.24
    dcc
    0.23
    桧
    0.23
     Caf
    0.23
     columns
    0.23
    <context
    0.22
    Activations Density 0.005%

    No Known Activations