© 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. 30-TRANSCODER-HP
    7. 96941
    Prev
    Next
    INDEX
    Explanations

    volume

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     collections
    -0.90
    æĶ¶éĽĨ
    -0.88
     collection
    -0.87
    éĽĨ
    -0.86
     collected
    -0.79
     collecting
    -0.77
    collection
    -0.77
     collect
    -0.76
    collections
    -0.73
     collects
    -0.72
    POSITIVE LOGITS
     volume
    0.49
     Volume
    0.47
     volumes
    0.45
    volume
    0.42
    Volume
    0.41
    -volume
    0.41
    (volume
    0.40
    .volume
    0.39
    _volume
    0.39
    olume
    0.36
    Activations Density 0.930%

    No Known Activations