© 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. 49195
    Prev
    Next
    INDEX
    Explanations

    starting dates

    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
    hower
    -0.10
    éģ½
    -0.10
    æĢ¥éĢŁ
    -0.09
    MON
    -0.09
    виÑĤ
    -0.09
    çļĦèĥ½éĩı
    -0.09
    çĴĢ
    -0.09
    åı¦ä¸Ģç§į
    -0.09
    opus
    -0.08
    ONT
    -0.08
    POSITIVE LOGITS
    å¼Ģå§ĭäºĨ
    0.14
     ìĭľìŀij
    0.14
    å¼Ģå§ĭ
    0.13
     starts
    0.13
    beg
    0.12
    ãģĮå§ĭ
    0.12
     наÑĩина
    0.11
     start
    0.11
    å§ĭäºİ
    0.11
    starts
    0.11
    Activations Density 0.172%

    No Known Activations