© 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. 9521
    Prev
    Next
    INDEX
    Explanations

    immediate refund

    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
    认è´Ń
    -0.09
    为人
    -0.09
    ä¸İåħ¶ä»ĸ
    -0.09
    é¢Ħ订
    -0.08
    é¢ĦåijĬ
    -0.08
    igy
    -0.08
     Trem
    -0.08
    æ±īåŃIJ
    -0.07
    ä¸Ģé¡¿
    -0.07
     solic
    -0.07
    POSITIVE LOGITS
    éĢĢè´§
    0.12
    第ä¸ĢæŶéĹ´
    0.10
    管çIJĨä½ĵç³»
    0.10
    æĥĭ
    0.09
    .ease
    0.09
    åĽ½éĻħè´¸æĺĵ
    0.09
    èij©
    0.09
    å®ħ
    0.09
    å¤ĦçIJĨ
    0.09
    .Resize
    0.09
    Activations Density 0.016%

    No Known Activations