© 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. 7353
    Prev
    Next
    INDEX
    Explanations

    during a certain period or count

    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
    æĤ²åĵĢ
    -0.10
    两年
    -0.10
    两个æľĪ
    -0.09
    åĩłä¸ªæľĪ
    -0.09
    ä¸ī个æľĪ
    -0.09
    ä¸īå¹´
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
    åĩłå¹´
    -0.09
    å¥Ĺè£ħ
    -0.08
    ä¸įåħĭ
    -0.08
    POSITIVE LOGITS
    TIM
    0.10
    èĮĥ
    0.09
    alo
    0.08
    è¿ŀ
    0.08
    autoload
    0.08
     TIM
    0.08
    _SEQ
    0.08
     اØŃد
    0.08
     cron
    0.08
     ÑĢиÑģк
    0.08
    Activations Density 0.169%

    No Known Activations