© 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. 37473
    Prev
    Next
    INDEX
    Explanations

    and lists of actions

    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
    ç¾Ĭ
    -0.11
    outu
    -0.11
    æĻºåķĨ
    -0.10
    æį®æѤ
    -0.10
    ç¾Ĭæ¯Ľ
    -0.09
    è°ĪæģĭçĪ±
    -0.09
    -Sep
    -0.09
    _chance
    -0.09
    åŃ³
    -0.09
    èŀį为ä¸Ģä½ĵ
    -0.09
    POSITIVE LOGITS
     пÑĢием
    0.09
     reputable
    0.09
     Frag
    0.08
    åľĥ
    0.08
    éħį
    0.08
    æĪĸåħ¶ä»ĸ
    0.08
    çIJĨ解åĴĮ
    0.08
    scape
    0.07
    è¿ĻäºĽä¸ľè¥¿
    0.07
    æ³£
    0.07
    Activations Density 0.082%

    No Known Activations