© 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. 39962
    Prev
    Next
    INDEX
    Explanations

    ALTER or MODIFY

    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
    åĽ´
    -0.09
    OME
    -0.09
    äºĪ
    -0.08
     bron
    -0.08
    éĢĤåºĶ
    -0.08
    /host
    -0.08
    æIJ¬å®¶
    -0.08
    ä¸Ģæ³¢
    -0.08
    çļĦéĴ±
    -0.08
    holm
    -0.08
    POSITIVE LOGITS
    çŁŃ缺
    0.10
    çľĭä¸įæĩĤ
    0.10
    /cs
    0.09
    æľªç»ıæİĪæĿĥ
    0.09
    ç¨Ģ缺
    0.09
    篡
    0.09
    æı©
    0.09
     gá»ijc
    0.09
     Tam
    0.09
    æĤĦæĤĦ
    0.09
    Activations Density 0.108%

    No Known Activations