© 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. 49952
    Prev
    Next
    INDEX
    Explanations

    pauses or separators

    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
    æīĢä»¥åľ¨
    -0.12
    çĶļèĩ³è¿ĺ
    -0.11
    ä¸įè¦ģåĨį
    -0.11
    åį´åıĪ
    -0.10
    ä½Ĩä¹Ł
    -0.10
    åı¯è°ĵ
    -0.10
    èĢĮä¸Ķè¿ĺ
    -0.10
     tháºŃm
    -0.09
    æ§İ
    -0.09
    LER
    -0.09
    POSITIVE LOGITS
    åŁºç¡Ģä¸Ĭ
    0.09
    ç»ĵ
    0.09
    éĻĽ
    0.08
    /how
    0.08
     Hel
    0.08
    åį°è±¡
    0.08
     despite
    0.07
    Hel
    0.07
    象
    0.07
    ä¸Ģç«Ļ
    0.07
    Activations Density 0.044%

    No Known Activations