© 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. 25-TRANSCODER-HP
    7. 106932
    Prev
    Next
    INDEX
    Explanations

    Technical, reviews, and questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĦĻ
    -0.33
    ä¼ĺéĢī
    -0.29
     McCoy
    -0.28
    æľĿ
    -0.27
    æ¶Ĥ
    -0.26
     painting
    -0.26
     paintings
    -0.25
    æĭĽèĤ¡
    -0.25
     organic
    -0.24
    éĩĩæijĺ
    -0.24
    POSITIVE LOGITS
    otta
    0.28
    ç»Ļä½łä»¬
    0.27
    æĪ¬
    0.27
    ounder
    0.26
     Gunn
    0.26
    ouns
    0.26
    éĴĪ
    0.25
     è¾ĵ
    0.25
    Been
    0.24
    è¿Ļæĸ¹éĿ¢
    0.24
    Activations Density 0.907%

    No Known Activations