© 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. 29890
    Prev
    Next
    INDEX
    Explanations

    visual/audio media and quality

    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
    è¿°
    -0.10
    大éĿ¢ç§¯
    -0.10
    æīĵæī®
    -0.09
    çŃĸ
    -0.09
    åĬĿ
    -0.09
    æ´ŀ
    -0.09
    icing
    -0.08
    羣çĪ±
    -0.08
    åį¸
    -0.08
    /widget
    -0.08
    POSITIVE LOGITS
    èĢ¦
    0.08
    æłī
    0.08
    æ®ĭå¿į
    0.08
    åĿİ
    0.08
    PointerType
    0.08
    _hom
    0.08
    嬴
    0.08
    ula
    0.08
    ä¿ı
    0.08
    äºĨä¸Ģæī¹
    0.07
    Activations Density 0.342%

    No Known Activations