© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21420
    Prev
    Next
    INDEX
    Explanations

    no matter how

    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
    å·®ä¸įå¤ļ
    -0.10
     mak
    -0.09
    éŀĺ
    -0.08
    lexical
    -0.08
    odes
    -0.08
    çĿ¥
    -0.08
    ÑĥÑīе
    -0.08
    animations
    -0.08
     Budd
    -0.08
    秩
    -0.08
    POSITIVE LOGITS
    lich
    0.11
    å¤ļä¹Ī
    0.10
    éĥ½ä¸įèĥ½
    0.10
    è¯ķçĿĢ
    0.10
    ç»ĦåIJĪ
    0.10
    飧æĢ§
    0.10
    æĥ³æĥ³
    0.09
    çīĴ
    0.09
    ä¹Łä¸įèĥ½
    0.09
    å¤ļåľ°
    0.09
    Activations Density 0.026%

    No Known Activations