© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50857
    Prev
    Next
    INDEX
    Explanations

    within a measure of time

    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
    CHK
    -0.10
    çĸĶ
    -0.09
    æ¯Ķèµ·
    -0.09
    éĻĮ
    -0.09
    ánh
    -0.09
    onto
    -0.09
    亲çĪ±çļĦ
    -0.09
    çģŀ
    -0.09
    anti
    -0.09
    ../
    -0.08
    POSITIVE LOGITS
    æİ¥åĪ°
    0.10
     being
    0.09
    è¿ĽåŁİ
    0.09
    大åѦæ¯ķä¸ļ
    0.09
    ilt
    0.08
    èĩªå·±çļĦ
    0.08
    æľīæľºä¼ļ
    0.08
    zeitig
    0.08
    iture
    0.08
    è¸ıåħ¥
    0.08
    Activations Density 0.007%

    No Known Activations