© 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. 35751
    Prev
    Next
    INDEX
    Explanations

    progress and progression

    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
    arah
    -0.09
    æģĥ
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.08
    ulfilled
    -0.08
    iable
    -0.08
    isle
    -0.08
    éļ¾åıĹ
    -0.08
    æľ¬ç«Ļ
    -0.08
    raries
    -0.08
    æİĺ
    -0.08
    POSITIVE LOGITS
    èĩ³æѤ
    0.11
    åĩłæŃ¥
    0.10
    ä¸įäºĨ
    0.09
    ä¸ĩåĪĨ
    0.09
     Roz
    0.09
    éŀ®
    0.09
    åİ»çľĭçľĭ
    0.09
    çIJĽ
    0.09
     onto
    0.08
    nel
    0.08
    Activations Density 0.022%

    No Known Activations