© 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. 48820
    Prev
    Next
    INDEX
    Explanations

    it was worth it

    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
    ä¹ĭç¾İ
    -0.11
     ÑĨелÑĮÑİ
    -0.09
    mus
    -0.09
    åħ¶æ¬¡æĺ¯
    -0.09
    人æ°ijç½ij
    -0.09
    åħ¬æĬ¥
    -0.09
    éĢıè§Ĩ
    -0.09
    uet
    -0.09
    æĺ¯æ¯Ķè¾ĥ
    -0.08
    æĺ¯å¾Ī
    -0.08
    POSITIVE LOGITS
    /disable
    0.10
    alse
    0.09
    ris
    0.08
    ools
    0.08
    IRO
    0.08
    主ç¼ĸ
    0.08
    overall
    0.08
    tero
    0.08
    -looking
    0.08
     бо
    0.08
    Activations Density 0.005%

    No Known Activations