© 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. 36884
    Prev
    Next
    INDEX
    Explanations

    fishing efficiency

    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
     bicy
    -0.10
    çĭ®åŃIJ
    -0.09
    ìľµ
    -0.08
    å¸Ķ
    -0.08
     bicycle
    -0.08
    èģª
    -0.08
    Fans
    -0.08
     Gupta
    -0.08
     unint
    -0.08
    soup
    -0.08
    POSITIVE LOGITS
    éĴĵ
    0.17
    饵
    0.14
    ðŁİ£
    0.12
     angl
    0.11
    åĻ¨æĿIJ
    0.11
    éĴĵé±¼
    0.11
    ç«¿
    0.11
    æ¸Ķ
    0.10
    é³ľ
    0.10
    æĸ°æīĭ
    0.10
    Activations Density 0.081%

    No Known Activations