© 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. 19371
    Prev
    Next
    INDEX
    Explanations

    celebrity news and achievements

    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
    个çĻ¾åĪĨ
    -0.09
    èĻij
    -0.09
    à¸Ļะ
    -0.09
    æĪĸå¤ļ
    -0.09
    讲å¸Ī
    -0.08
    æĢª
    -0.08
    Cancelable
    -0.08
    æĵĢ
    -0.08
    飬
    -0.08
    è´§æºIJ
    -0.08
    POSITIVE LOGITS
    æĹłä¸į
    0.11
    é©»
    0.10
    说çĿĢ
    0.10
    å¾ģæľį
    0.10
    éĿłçĿĢ
    0.09
    æĹłæķ°
    0.09
    绽
    0.09
    æĥĬèī³
    0.09
    ä½ľåĩºäºĨ
    0.09
    awe
    0.08
    Activations Density 0.078%

    No Known Activations