© 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. 26621
    Prev
    Next
    INDEX
    Explanations

    suffix "-ovich" or "-ovsky"

    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
    ä¾ĥ
    -0.12
    èĵ¦
    -0.09
    ä¸ĢåĪ»
    -0.09
    æ¥Ķ
    -0.09
    çİĦ
    -0.09
     rhe
    -0.09
    åıĤèĤ¡
    -0.09
    æĥļ
    -0.09
    åı¯åľ¨
    -0.09
    åŃĹæł·
    -0.09
    POSITIVE LOGITS
    æ²»å®ī
    0.09
    drs
    0.09
    çĻ»
    0.08
    æ·¹
    0.08
    çĸı
    0.08
    éŃĶ鬼
    0.08
    ç»ķ
    0.08
    è·ĥ
    0.08
    ester
    0.08
    ertype
    0.08
    Activations Density 0.018%

    No Known Activations