© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    scratches, marks, cracks, punctures

    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
    èģĶ绾
    -0.10
    oble
    -0.09
    å¼Ģåĩº
    -0.09
    æ®ĭå¿į
    -0.09
    åīľ
    -0.09
    æ®ĭéħ·
    -0.09
    èĩŃ
    -0.09
    8
    -0.09
    æĹłç©·
    -0.08
    contact
    -0.08
    POSITIVE LOGITS
    ä¹ĭå¤Ħ
    0.09
    akk
    0.09
    swith
    0.09
    æľīæľºç»ĵåIJĪ
    0.09
    uns
    0.08
    å¿ĥåĬ¨
    0.08
    æŁ³å·ŀ
    0.08
    è¢Ń
    0.08
    avan
    0.08
    -turned
    0.08
    Activations Density 0.035%

    No Known Activations