© 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. 49478
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
    è°ħ
    -0.11
    ä¸įè§ģäºĨ
    -0.09
    okane
    -0.09
     Means
    -0.09
    å¾ĭå¸ĪäºĭåĬ¡
    -0.08
    è§īæĤŁ
    -0.08
    forme
    -0.08
    ooter
    -0.08
    ä½łæĥ³
    -0.08
    æį·
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģ个
    0.12
    éĿ¢å¯¹
    0.11
    è¿İæĿ¥
    0.10
    éĿ¢ä¸´
    0.10
    éģĩåĪ°äºĨ
    0.10
    è¿İæĿ¥äºĨ
    0.10
    éĿ¢ä¸´çļĦ
    0.09
    æīĵ交éģĵ
    0.09
    éĿ¢ä¸´çĿĢ
    0.09
    éĿ¢å°į
    0.09
    Activations Density 0.062%

    No Known Activations