© 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. 17276
    Prev
    Next
    INDEX
    Explanations

    German patent numbers

    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
    çĭ¸
    -0.10
    ible
    -0.09
    åıijå±ķ空éĹ´
    -0.09
    ä»ħ次äºİ
    -0.08
    ä¸Ģ个人
    -0.08
     Ether
    -0.08
    itar
    -0.08
    ç»ī
    -0.08
    æĽĻ
    -0.08
    å°ıåĮº
    -0.08
    POSITIVE LOGITS
    åĨ¥
    0.09
    æĮĩæľĽ
    0.09
     Pavilion
    0.08
    ä¸ĢåĪ»
    0.08
    ESIS
    0.08
    æŃ£ä¹ī
    0.08
    å«ī
    0.08
    å±¥
    0.08
    大åŁİå¸Ĥ
    0.08
    æ¯įåħ¬åı¸
    0.08
    Activations Density 0.026%

    No Known Activations