© 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. 43977
    Prev
    Next
    INDEX
    Explanations

    period

    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
    çĪ¶æ¯į
    -0.33
    çĪ¸å¦Ī
    -0.32
     dads
    -0.32
     Auditor
    -0.30
     moms
    -0.30
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.29
    å¦Īå¦Ī
    -0.28
    igers
    -0.27
    ĽĦ
    -0.27
     licensors
    -0.26
    POSITIVE LOGITS
     most
    0.36
     Most
    0.35
    æĶ¸
    0.32
    Most
    0.30
     MOST
    0.27
     Young
    0.27
     education
    0.27
    young
    0.27
     tract
    0.26
    most
    0.25
    Activations Density 0.015%

    No Known Activations