© 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. 27946
    Prev
    Next
    INDEX
    Explanations

    free duplication rights entitlement

    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
    ä¼ı
    -0.10
    æİ¡
    -0.09
    æľĢéĢĤåIJĪ
    -0.08
    ym
    -0.08
    ikon
    -0.08
     Spam
    -0.08
     protector
    -0.08
    çĮ®è¡Ģ
    -0.08
    åķ¤
    -0.08
    /misc
    -0.08
    POSITIVE LOGITS
    é»ĺ
    0.12
    第ä¸ī次
    0.10
    æĭ·
    0.09
    bon
    0.09
     chá
    0.09
    å°ıå¾®ä¼ģä¸ļ
    0.09
    PILE
    0.09
    èī°èĭ¦
    0.09
    é»İæĺİ
    0.09
    读åIJİ
    0.09
    Activations Density 0.071%

    No Known Activations