© 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. 33404
    Prev
    Next
    INDEX
    Explanations

    acquire knowledge or clarity

    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
    æĺĶ
    -0.09
    åİĨ
    -0.08
    inst
    -0.08
    æĹ¢æľī
    -0.08
    æİĪ
    -0.08
    ãĥ¼ãĥĪ
    -0.08
    tip
    -0.08
    樾
    -0.07
    éļıæīĭ
    -0.07
    ange
    -0.07
    POSITIVE LOGITS
    æĺİæľĹ
    0.16
    çľĭæ¸ħ
    0.11
    æīįåı¯ä»¥
    0.10
    åģļå®Į
    0.10
    æıŃæĻĵ
    0.10
    ä»İ容
    0.10
    æŃ£å¼ı
    0.10
    è¡·
    0.10
    èĩ§
    0.09
    èµĸ以
    0.09
    Activations Density 0.070%

    No Known Activations