© 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. 22159
    Prev
    Next
    INDEX
    Explanations

    painting, theatre, city

    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
    ÙĤار
    -0.09
    åİĨåı²æĸĩåĮĸ
    -0.09
    éķ¿å¯¿
    -0.09
    åij½ä¸Ń
    -0.09
    æ±
    -0.08
    é£İæĻ¯
    -0.08
     اÙĦأخ
    -0.08
    oss
    -0.08
    çļ®èĤ¤çĹħ
    -0.08
    çĬ
    -0.08
    POSITIVE LOGITS
     szczeg
    0.09
    è½½ä½ĵ
    0.08
    央
    0.08
    é¢ĵ
    0.08
    rei
    0.08
    -place
    0.08
     Walters
    0.08
    4
    0.08
    mere
    0.08
    icycle
    0.08
    Activations Density 0.045%

    No Known Activations