© 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. 95176
    Prev
    Next
    INDEX
    Explanations

    Un

    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
     whether
    -0.30
    whether
    -0.28
    ä¸įèĥ½ä¸ºç©º
    -0.28
     Corpor
    -0.27
     Stateless
    -0.27
    ноÑģÑĤи
    -0.26
    ynos
    -0.26
     Whether
    -0.26
     Frequ
    -0.26
    Whether
    -0.25
    POSITIVE LOGITS
    hdl
    0.29
    åıĹ
    0.29
    çĪĨ
    0.28
    缴åĪ°
    0.27
    VEC
    0.27
    hir
    0.26
    欲
    0.26
    ALES
    0.26
    until
    0.26
    æķ¢
    0.26
    Activations Density 0.003%

    No Known Activations