© 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. 26650
    Prev
    Next
    INDEX
    Explanations

    happened / happens / 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
    dap
    -0.09
    禳
    -0.09
    姿
    -0.08
    è´Łè½½
    -0.08
    åıŁ
    -0.08
    (forKey
    -0.08
    éķķ
    -0.08
    ç»ļ丽
    -0.08
    arde
    -0.08
    å¤įä»ĩ
    -0.08
    POSITIVE LOGITS
    è¿Ļç§įæĥħåĨµ
    0.19
     happened
    0.19
    åıijçĶŁ
    0.18
     happens
    0.18
     happen
    0.18
    åıijçĶŁçļĦ
    0.17
    åıijçĶŁåľ¨
    0.17
    çĻ¼çĶŁ
    0.17
     ÑģлÑĥÑĩ
    0.16
    çļĦåıijçĶŁ
    0.16
    Activations Density 0.066%

    No Known Activations