© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2939
    Prev
    Next
    INDEX
    Explanations

    this/last week/month/year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŀ¢
    -0.10
    éľ²å¤©
    -0.10
    èĥĮåIJİ
    -0.10
    ippy
    -0.09
    gewater
    -0.09
    ÙĬÙĩ
    -0.09
     Rossi
    -0.09
    Scr
    -0.08
    é¦ĭ
    -0.08
    åĩºæĿ¥
    -0.08
    POSITIVE LOGITS
    éĥ½æľīèĩªå·±
    0.09
    æĹłçº¿
    0.08
    ä¸Ĭæ¼Ķ
    0.08
    ãģĭãģijãģ¦
    0.08
    å±ķå¼Ģ
    0.08
    åĽŀ头çľĭ
    0.08
    åıij声
    0.08
    etween
    0.08
    æµģ转
    0.08
    ened
    0.08
    Activations Density 0.054%

    No Known Activations