© 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. 9217
    Prev
    Next
    INDEX
    Explanations

    might or may be

    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
     freder
    -0.10
    注å®ļ
    -0.09
    æ½®
    -0.08
    çĽij管éĥ¨éŨ
    -0.08
    bane
    -0.08
    abic
    -0.08
     frog
    -0.08
    borg
    -0.08
    .ERR
    -0.08
    ÙĬØ·
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.10
    é»ĺ
    0.10
    å¾®å¦Ļ
    0.09
    rium
    0.09
    ula
    0.09
     somehow
    0.08
    ç®ĹäºĨ
    0.08
    æŃ£å®Ĺ
    0.08
    ä¹łæĥ¯
    0.08
    æĺ¯æĪijçļĦ
    0.08
    Activations Density 0.072%

    No Known Activations