© 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. 20490
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
    IFY
    -0.10
    æİĮæı¡äºĨ
    -0.10
    åijĨ
    -0.09
    cant
    -0.09
    agers
    -0.09
    ç»ĻåĩºäºĨ
    -0.09
    AGER
    -0.09
    egas
    -0.09
    éĺ´
    -0.08
    ãģ¦ãĤĭ
    -0.08
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.12
    íķĺê²łìĬµëĭĪëĭ¤
    0.09
    è¿Ļ个èģĮä¸ļ
    0.09
    åĩ«
    0.09
    éĵį
    0.09
    ç¡®å®ŀæĺ¯
    0.08
    á»ķ
    0.08
    羣æŃ£
    0.08
    ç¼´
    0.08
    çĻ«çĹ«çĹħ
    0.08
    Activations Density 0.061%

    No Known Activations