© 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. 52154
    Prev
    Next
    INDEX
    Explanations

    something other or like

    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
    æ²±
    -0.08
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    åĺ¿
    -0.08
    æģķ
    -0.08
    dam
    -0.08
    æĺ¯ä¸ĢåIJį
    -0.08
    ä¸Ģå¼ł
    -0.07
    åķĨæĬ¥
    -0.07
     dong
    -0.07
    edo
    -0.07
    POSITIVE LOGITS
    piler
    0.11
    çļĦä¸ľè¥¿
    0.10
    çĮ¥
    0.10
    rors
    0.10
    ä¸į符åIJĪ
    0.10
    åIJīåĪ©
    0.10
    _generate
    0.09
    çĨŁæĤī
    0.09
    質
    0.09
    å¤įæĿĤ
    0.09
    Activations Density 0.023%

    No Known Activations