© 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. 27-TRANSCODER-HP
    7. 58429
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æıIJä¾Ľä¼ĺè´¨
    -0.28
    çĻ¾å¼º
    -0.27
    建设çĶ¨åľ°
    -0.27
    æİĪä¿¡
    -0.27
     deser
    -0.27
    .Deserialize
    -0.27
    çŁ¥å·±
    -0.26
    çľ·
    -0.25
    åĬ£åĬ¿
    -0.25
    ropolis
    -0.24
    POSITIVE LOGITS
    å¼ĢéŨ
    0.27
    åĮ¹
    0.27
    oze
    0.26
     Kam
    0.26
    iale
    0.26
    izza
    0.25
    ITE
    0.25
    ä¸ĸä¸Ĭ
    0.24
    idal
    0.24
    pha
    0.24
    Activations Density 0.002%

    No Known Activations