© 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. 94905
    Prev
    Next
    INDEX
    Explanations

    choices and desires

    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
    æľīä»Ģä¹Ī
    -0.29
    å®Įåħ¨æ²¡æľī
    -0.28
    æľīä¸Ģå®ļ
    -0.26
    åħ¨åĽ½äººæ°ij
    -0.25
    .dtd
    -0.25
    éĥ½æľīèĩªå·±
    -0.25
    Injected
    -0.25
    æµĵ缩
    -0.24
    è¿ĺéľĢè¦ģ
    -0.24
    åĪ»æĦı
    -0.24
    POSITIVE LOGITS
    ìĿµ
    0.34
    oley
    0.30
    ideos
    0.28
     may
    0.28
    æĹ¥è®¯
    0.27
    ijken
    0.26
    profit
    0.25
    -bin
    0.25
    well
    0.25
    ÑĮе
    0.24
    Activations Density 0.072%

    No Known Activations