© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20415
    Prev
    Next
    INDEX
    Explanations

    you can guarantee a

    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
    æ³ĵ
    -0.09
    ivec
    -0.09
    éĻ
    -0.09
    ï¸ı
    -0.09
    å¼ĩ
    -0.09
    å·´
    -0.08
    éķ¿çĽ¸
    -0.08
    ToInt
    -0.08
     ming
    -0.08
    æĪĸ许æĺ¯
    -0.08
    POSITIVE LOGITS
     quis
    0.10
    owitz
    0.08
    çijĽ
    0.08
    移
    0.08
    hek
    0.08
    ç´§æī£
    0.08
    æ·±åħ¥å¼Ģå±ķ
    0.08
     certainly
    0.08
    ä»ĸ们ä¼ļ
    0.08
    åĨ°éĽª
    0.08
    Activations Density 0.036%

    No Known Activations