© 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. 38173
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
     неÑģколÑĮ
    -0.09
     пÑĢедоÑģÑĤавлен
    -0.09
     благодаÑĢ
    -0.08
    ä¸ĬäºĨ
    -0.08
     Matth
    -0.08
    çľ¼çķĮ
    -0.08
    对äºİæĪij们
    -0.08
    æĪijèĩªå·±
    -0.08
    æį®ä»ĭç»į
    -0.08
    Atomic
    -0.08
    POSITIVE LOGITS
     Millennium
    0.09
    æĹ¢çĦ¶
    0.09
    ÅĤÄħ
    0.08
    äººåľ¨
    0.08
     Suite
    0.08
    chl
    0.08
     ***
    0.08
    odus
    0.08
    欢è¿İ
    0.08
    åĩºæĿ¥çļĦ
    0.08
    Activations Density 0.543%

    No Known Activations