© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60603
    Prev
    Next
    INDEX
    Explanations

    assistance with

    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
    Negative Logits
    æ¹ľ
    -0.09
    ä¸ĢæŦ
    -0.09
    ihu
    -0.08
    æ±Ĺ
    -0.08
    çĹĶ
    -0.08
    计åĪĴ
    -0.08
    .metadata
    -0.08
    RECT
    -0.08
    è¸ı
    -0.08
    ìĭľíĹĺ
    -0.08
    POSITIVE LOGITS
    éĿ¢åŃĶ
    0.10
    èİ·å¾ĹæĦŁ
    0.09
    ä¸ĵåijĺ
    0.09
    cie
    0.09
    osl
    0.09
    èĩ³æѤ
    0.09
    ç¨
    0.09
    åij»
    0.08
    ald
    0.08
    æ·ħ
    0.08
    Activations Density 0.009%

    No Known Activations