© 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. 95173
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
     mounted
    -0.31
     positioned
    -0.30
    mounted
    -0.28
    衲
    -0.28
     seated
    -0.26
    located
    -0.25
    onaut
    -0.25
     located
    -0.25
    icans
    -0.25
    ç½®äºİ
    -0.24
    POSITIVE LOGITS
     rich
    0.37
    å¯Į
    0.33
    rich
    0.33
     Rich
    0.31
     richer
    0.30
     only
    0.29
    Rich
    0.29
     circle
    0.29
     richest
    0.29
     circles
    0.29
    Activations Density 0.885%

    No Known Activations