© 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. 32-TRANSCODER-HP
    7. 40978
    Prev
    Next
    INDEX
    Explanations

    shift

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åı¯æĥ³
    -0.27
    og
    -0.25
    erator
    -0.25
    DRAM
    -0.24
    æݧèĤ¡
    -0.23
    ä¹ı
    -0.23
    èIJ½åľ°
    -0.23
    ustom
    -0.23
     Sons
    -0.23
    oad
    -0.23
    POSITIVE LOGITS
     shift
    1.03
    shift
    0.94
     shifts
    0.92
     Shift
    0.91
    移
    0.91
    Shift
    0.90
     shifting
    0.88
     shifted
    0.85
    _shift
    0.84
    -shift
    0.84
    Activations Density 0.001%

    No Known Activations