© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12360
    Prev
    Next
    INDEX
    Explanations

    want to get

    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
    Negative Logits
    妨
    -0.12
    çĩĥæĸĻ
    -0.10
    èįĽ
    -0.10
     Hud
    -0.10
    éĭª
    -0.09
    åĽłä¸ºå®ĥ
    -0.09
    .ba
    -0.09
    åĬĽæ±Ĥ
    -0.09
    éĵº
    -0.08
    çľĭä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
    볤
    0.09
    èĩªåĬ¨åĮĸ
    0.09
    æĪIJåŀĭ
    0.08
    æµģæ°´
    0.08
    anced
    0.08
    .IsNull
    0.08
    çĻ¾èĬ±
    0.08
    abal
    0.08
     ÑģоглаÑģ
    0.08
    天ä¸Ĭ
    0.08
    Activations Density 0.020%

    No Known Activations