© 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. 40825
    Prev
    Next
    INDEX
    Explanations

    conce

    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
    andy
    -0.30
    å±Ģ
    -0.26
     sit
    -0.26
    éŵ
    -0.25
     resid
    -0.25
    çĽ¸å·®
    -0.25
    åįļè§Ī
    -0.25
    ëŀij
    -0.24
     tang
    -0.24
    ÑĮÑİ
    -0.24
    POSITIVE LOGITS
     blind
    0.32
     bel
    0.29
     mask
    0.29
     masks
    0.29
    blind
    0.28
    mask
    0.28
    çĽĸ
    0.28
    è¿·æĥij
    0.28
    unate
    0.27
     usize
    0.27
    Activations Density 0.000%

    No Known Activations