© 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. 58607
    Prev
    Next
    INDEX
    Explanations

    voltage

    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
     schn
    -0.27
     noses
    -0.27
    blick
    -0.26
     Mojo
    -0.26
     nose
    -0.25
     tra
    -0.25
     tracer
    -0.25
    _path
    -0.24
     chart
    -0.24
     INA
    -0.24
    POSITIVE LOGITS
    çĶµåİĭ
    0.37
     volt
    0.37
     voltage
    0.35
     Volt
    0.35
    çĶµæºIJ
    0.34
    ä¾ĽçĶµ
    0.33
     Voltage
    0.32
    çĶµæµģ
    0.31
    Voltage
    0.29
    æĿ¥çĶµ
    0.28
    Activations Density 0.008%

    No Known Activations