© 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. 54087
    Prev
    Next
    INDEX
    Explanations

    appointment for an event

    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
    饴
    -0.11
    moid
    -0.09
    æĩµ
    -0.09
    åľ°ä¸Ń
    -0.08
    ITA
    -0.08
    çĽ¯
    -0.08
    迷人
    -0.08
    yas
    -0.08
    eto
    -0.08
    å¹¿æ³ĽåºĶçĶ¨
    -0.08
    POSITIVE LOGITS
    ä¸ĵ访
    0.10
    åķľ
    0.10
    访è°Ī
    0.09
    åİ®
    0.09
    èį
    0.09
    ä¸İä¼Ĺ
    0.09
    bes
    0.08
    åįĬ个å°ıæŶ
    0.08
    约è°Ī
    0.08
    她们
    0.08
    Activations Density 0.138%

    No Known Activations