© 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. 21367
    Prev
    Next
    INDEX
    Explanations

    during conversation

    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
    æ´¾
    -0.11
    çī¹ç§į
    -0.09
    ä¸Ģå¤ľ
    -0.09
    æļ´åĬĽ
    -0.08
     Trom
    -0.08
    åŃĹæł·
    -0.08
    çİĭèĢħ
    -0.08
    éĻį
    -0.08
    欺éªĹ
    -0.08
    éĢģåİ»
    -0.08
    POSITIVE LOGITS
    æīĵæĸŃ
    0.12
    åIJ¬ä¼Ĺ
    0.11
    ç«Ļèµ·æĿ¥
    0.11
    åıijè¨Ģ人
    0.10
    åIJ¬å¾Ĺ
    0.10
    åıijè¨Ģ
    0.10
     interruptions
    0.10
    æ»Ķ
    0.10
    æĬĬæݧ
    0.09
    èħ®
    0.09
    Activations Density 0.060%

    No Known Activations