© 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. 25-TRANSCODER-HP
    7. 109572
    Prev
    Next
    INDEX
    Explanations

    Technical and Specific References

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    orean
    -0.28
    inish
    -0.26
    @"
    -0.25
    ãĤĤå¤ļãģı
    -0.24
    ISH
    -0.24
    uzzi
    -0.24
    pei
    -0.23
    culate
    -0.23
    orate
    -0.23
    ãĥªãĥ¼
    -0.23
    POSITIVE LOGITS
    åı¦ä¸Ģ
    1.16
    åı¦ä¸Ģç§į
    1.05
     another
    1.02
    åı¦ä¸Ģ个
    1.02
     differently
    0.95
    åı¦å¤ĸä¸Ģ个
    0.93
     other
    0.93
     different
    0.92
    another
    0.90
    åı¦å¤ĸ
    0.89
    Activations Density 0.970%

    No Known Activations