© 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. 95013
    Prev
    Next
    INDEX
    Explanations

    rights

    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
    baugh
    -0.32
    celain
    -0.29
    .analysis
    -0.28
     entry
    -0.27
    lint
    -0.26
    .entry
    -0.26
     layouts
    -0.26
     undo
    -0.25
    imson
    -0.25
     erect
    -0.24
    POSITIVE LOGITS
    eor
    0.28
    泡
    0.26
    arer
    0.26
    -mon
    0.26
    åİ»
    0.26
    ço
    0.26
     av
    0.25
    åīij
    0.25
    ram
    0.25
    oe
    0.25
    Activations Density 0.060%

    No Known Activations