© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38373
    Prev
    Next
    INDEX
    Explanations

    season

    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
    讶
    -0.11
    ä¸ĸä¸Ĭ
    -0.11
    ç»ĪçĶŁ
    -0.10
    æĸ¹å¼ıè¿Ľè¡Į
    -0.10
    å¸ĺ
    -0.10
    ä¸ĸçķĮä¸Ĭ
    -0.10
    å¸Ĥåľºä¸»ä½ĵ
    -0.10
    ä»İå°ıå°±
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    èį«
    -0.09
    POSITIVE LOGITS
    çĭ¬
    0.09
     Hart
    0.08
    åĶ¯
    0.08
    isco
    0.08
     coff
    0.07
     bol
    0.07
    ous
    0.07
    COMP
    0.07
     Bol
    0.07
     rig
    0.07
    Activations Density 0.009%

    No Known Activations