© 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. 31340
    Prev
    Next
    INDEX
    Explanations

    once

    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
    ä½łçİ°åľ¨
    -0.13
    建æĪIJåIJİ
    -0.13
    æĪij们çİ°åľ¨
    -0.12
     now
    -0.12
    æ¯ķä¸ļåIJİ
    -0.12
    çİ°åľ¨
    -0.12
    æĪijçİ°åľ¨
    -0.12
    ä»Ĭ天
    -0.11
    åĪ°æľŁ
    -0.10
    çľ¼ä¸ĭ
    -0.10
    POSITIVE LOGITS
    æīįåıijçİ°
    0.13
    ç«ĭåį³
    0.11
    ç«ĭåĪ»
    0.11
    å°±å¼Ģå§ĭ
    0.11
     Ùħباشرة
    0.09
    移
    0.09
    纶
    0.09
    WSC
    0.09
    缸å½ĵ
    0.09
    ä¸įåĨį
    0.09
    Activations Density 0.150%

    No Known Activations