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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36747
    Prev
    Next
    INDEX
    Explanations

    comparisons including vs

    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
    åĽ½éĻħæľºåľº
    -0.08
    澤
    -0.08
    æĸ°ä¸Ģ代
    -0.08
    åĮĹæµ·
    -0.08
    æ°´åĩĨ
    -0.08
    	TokenName
    -0.08
    泡
    -0.08
    ãĥŀãĥ«
    -0.08
    æŀģå¤§åľ°
    -0.08
    çĨŁçŁ¥
    -0.08
    POSITIVE LOGITS
    èĻļå¼±
    0.09
    ront
    0.09
     Vulner
    0.09
    群éĩĮ
    0.08
    ä¸İåħ¶ä»ĸ
    0.08
    èĦ±è´«
    0.08
     vulnerable
    0.08
    yled
    0.08
    èĢģ人家
    0.08
     consistently
    0.07
    Activations Density 0.176%

    No Known Activations