© 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. 8459
    Prev
    Next
    INDEX
    Explanations

    devote, akt, uf

    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
    åı£æ°Ķ
    -0.11
    ï¸
    -0.10
    ousing
    -0.09
    身å¿ĥåģ¥åº·
    -0.09
    çĵ¯
    -0.09
    çĪ±åIJĥ
    -0.08
    主åŁİåĮº
    -0.08
     оказÑĭва
    -0.08
    enses
    -0.08
    产éĶĢ
    -0.08
    POSITIVE LOGITS
    ìŀħ
    0.09
    abad
    0.08
    ÑĨÑĥ
    0.08
    æ¡Ķ
    0.08
    .Unity
    0.08
     اعت
    0.08
    åĪ°ä½į
    0.08
     Planet
    0.08
     thú
    0.08
    æ°´åĩĨ
    0.08
    Activations Density 0.012%

    No Known Activations