© 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. 10241
    Prev
    Next
    INDEX
    Explanations

    occasions and times

    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
    ç²¾é«ĵ
    -0.10
    _TYPED
    -0.09
     обÑĢаз
    -0.09
    /*@
    -0.09
     ticking
    -0.09
    обÑĢаз
    -0.08
    æĤ£ä¸Ĭ
    -0.08
    楼ä¸ĭ
    -0.08
    ãĤŃãĥ£ãĥ³
    -0.08
    illin
    -0.08
    POSITIVE LOGITS
    æŶåĢĻ
    0.18
     occasions
    0.17
     times
    0.16
     moments
    0.16
     occasion
    0.15
    occasion
    0.14
    åľºåIJĪ
    0.14
    times
    0.13
    çļĦæŶåĢĻ
    0.13
     ÑģлÑĥÑĩа
    0.13
    Activations Density 0.087%

    No Known Activations