© 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. 10542
    Prev
    Next
    INDEX
    Explanations

    redaction or reduction

    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
    åѦéĹ®
    -0.08
    æİ¥åĬĽ
    -0.08
    èĢij
    -0.08
    æĦĨ
    -0.08
    EXTERNAL
    -0.08
    æŁIJç§įç¨ĭ度
    -0.07
    ï¸ı
    -0.07
    ä¸įåĩĨ
    -0.07
    æ§
    -0.07
    æīĢ以æĪij
    -0.07
    POSITIVE LOGITS
    å´Ľ
    0.09
    æĵĤ
    0.09
    çĪ±ç¾İ
    0.09
    å¸Ĥä¸Ńå¿ĥ
    0.09
    ohana
    0.09
    æĢķ
    0.09
    ysz
    0.09
    æĢĿ绪
    0.08
    lest
    0.08
    çIJ¢
    0.08
    Activations Density 0.412%

    No Known Activations