© 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. 51332
    Prev
    Next
    INDEX
    Explanations

    occurrences of "happen"

    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
    åĹij
    -0.10
    crit
    -0.10
    åĵĩ
    -0.09
    holes
    -0.09
    çĪ¬ä¸Ĭ
    -0.09
    اسÙĬ
    -0.09
    æ¿Ĵ临
    -0.09
    亲çĪ±
    -0.08
     MISS
    -0.08
    é©´
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģ
    0.09
    encer
    0.09
    naire
    0.09
    è¿ĩçļĦ
    0.08
     деÑĢ
    0.08
    inder
    0.08
     ÑģÑĤÑĢа
    0.08
     Sham
    0.08
    /be
    0.08
    ä¸įäºĨ
    0.08
    Activations Density 0.020%

    No Known Activations