© 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. 8009
    Prev
    Next
    INDEX
    Explanations

    winning or being confirmed

    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
    Not in Any Lists

    No Comments

    Negative Logits
     radicals
    -0.29
    åħħçĶµ
    -0.26
    åĽĽä¸ªæĦıè¯Ĩ
    -0.25
    sher
    -0.25
    ç»ĦåĽ¢
    -0.24
     shutil
    -0.24
     folds
    -0.24
    ä¸ĢåłĨ
    -0.24
     strategies
    -0.24
    ç¼Ī
    -0.24
    POSITIVE LOGITS
    iec
    0.30
    èĮĥ
    0.28
    .tie
    0.26
     Tin
    0.26
    \Auth
    0.25
    emu
    0.25
     EEPROM
    0.24
    好人
    0.23
     Ãĸzel
    0.23
    èĩªçĦ¶
    0.23
    Activations Density 0.001%

    No Known Activations