© 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. 38949
    Prev
    Next
    INDEX
    Explanations

    units of measurement or quantities

    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
    çĶľçĶľ
    -0.09
    éĢ¼
    -0.09
    åŃij
    -0.09
    æĹ¢èĥ½
    -0.09
    uve
    -0.09
    ุà¸ĩ
    -0.09
    gie
    -0.09
    akers
    -0.09
    ило
    -0.08
    arium
    -0.08
    POSITIVE LOGITS
    è°Ĭ
    0.09
    æ¯ı次éĥ½
    0.09
    è¿Ļä¸ªåľ°åĽ¾
    0.09
    åĪĨ彩
    0.09
    éĨī
    0.08
    寸
    0.08
    æĭľ
    0.08
    åľ¨è¿Ļ个
    0.08
    isle
    0.08
    åĬ¨æīĭ
    0.08
    Activations Density 0.117%

    No Known Activations