© 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. 34266
    Prev
    Next
    INDEX
    Explanations

    interaction analysis IPA

    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
    æĤ´
    -0.10
    åĽ¢
    -0.09
     Disconnect
    -0.09
    äºĴèģĶ
    -0.09
    宸
    -0.09
    红åĪ©
    -0.09
    éĴľ
    -0.08
    æİ¥åħ¥
    -0.08
    æ¯ı个æľĪ
    -0.08
    è½®
    -0.08
    POSITIVE LOGITS
    æ»Ķ
    0.08
    utter
    0.08
    å¤ķéĺ³
    0.08
    åıł
    0.08
    éĢĢ
    0.08
     Mattis
    0.08
    驾驶åijĺ
    0.08
     IPA
    0.08
    ilater
    0.08
    /el
    0.08
    Activations Density 0.069%

    No Known Activations