© 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. 61952
    Prev
    Next
    INDEX
    Explanations

    degrees of variation

    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
    åĵªæĢķ
    -0.11
    étr
    -0.09
    éĤ£æł·
    -0.09
    nqu
    -0.09
    åĬłåĢį
    -0.08
     egt
    -0.08
    ãģłãģ£ãģ¦
    -0.08
    åŁºçŁ³
    -0.08
    _sampler
    -0.08
    èĢĥåľº
    -0.08
    POSITIVE LOGITS
    äºĨäºĽ
    0.10
    ä½ĨçĶ±äºİ
    0.09
    常年
    0.09
    äºĨä¸ĢäºĽ
    0.09
    ç»ıèIJ¥æ´»åĬ¨
    0.09
    çĶ±äºİ
    0.08
    åİ¿æĶ¿åºľ
    0.08
    ä¹Łæ¯Ķè¾ĥ
    0.08
    è¾ĥ为
    0.08
    åħ¨å¹´
    0.08
    Activations Density 0.202%

    No Known Activations