© 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. 95042
    Prev
    Next
    INDEX
    Explanations

    mocking

    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
     vern
    -0.34
     Trib
    -0.28
    ç«¥
    -0.27
    ãĤµãĥ©
    -0.27
     sal
    -0.27
    boys
    -0.26
    ete
    -0.26
     tribes
    -0.25
    lbrace
    -0.25
    itor
    -0.25
    POSITIVE LOGITS
     deactivated
    0.29
    Hur
    0.27
    createUrl
    0.26
    Hooks
    0.26
    Bush
    0.26
    æĪijçļĦå¿ĥ
    0.26
    ApiController
    0.25
    æ¡ī
    0.25
    Cards
    0.25
    äºĶæĺŁ
    0.25
    Activations Density 0.882%

    No Known Activations