© 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. 31-TRANSCODER-HP
    7. 19970
    Prev
    Next
    INDEX
    Explanations

    based

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åŁºäºİ
    -0.67
     based
    -0.65
    Based
    -0.57
    _based
    -0.57
    based
    -0.57
     Based
    -0.57
    -based
    -0.38
    -Based
    -0.35
    ãģ«åŁºãģ¥
    -0.31
     using
    -0.31
    POSITIVE LOGITS
     upon
    0.65
     Upon
    0.56
    Upon
    0.51
    upon
    0.49
     strongly
    0.34
     heavily
    0.32
    åIJģ
    0.31
    ä¸ĬäºĨ
    0.30
     strictly
    0.30
     closely
    0.29
    Activations Density 0.237%

    No Known Activations