© 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. 63342
    Prev
    Next
    INDEX
    Explanations

    following a colon

    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
    第ä¸ī个
    -0.09
    çĤ¹å¤ļ
    -0.09
    ĮĢ
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    imus
    -0.08
    æĥ³åĪ°äºĨ
    -0.08
     descon
    -0.08
    itant
    -0.08
    çĽ¸äº²
    -0.08
    à¹Ģสมà¸Ń
    -0.08
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.14
    åĪĨåĪ«ä¸º
    0.12
    å¦Ĥä¸ĭ
    0.10
    åIJįåįķ
    0.10
    ä¾Ŀ次
    0.09
    æľºåŀĭ
    0.09
    éĽĢ
    0.09
    :
    0.09
    äº®çĽ¸
    0.09
    åĮħæĭ¬
    0.09
    Activations Density 0.166%

    No Known Activations