© 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. 17331
    Prev
    Next
    INDEX
    Explanations

    parts and upgrades

    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
     bid
    -0.09
    ç¾İ好
    -0.09
    9
    -0.08
    éŃĤ
    -0.08
     Charl
    -0.08
    稳
    -0.08
    ç¾İ好çļĦ
    -0.08
    destruct
    -0.08
    éĩİ
    -0.08
    Likes
    -0.08
    POSITIVE LOGITS
    讪
    0.09
     оÑĢганизаÑĨиÑı
    0.09
    ادة
    0.09
    æĮĤçīĮ
    0.09
    lsa
    0.09
    åħ¨è¿ĩç¨ĭ
    0.09
    åļı
    0.09
    è¾ķ
    0.09
    illow
    0.09
     bulund
    0.09
    Activations Density 0.019%

    No Known Activations