© 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. 2684
    Prev
    Next
    INDEX
    Explanations

    Canterbury church

    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
    åĩ¡æľ¬ç½ij
    -0.09
    esta
    -0.08
    æķ£
    -0.08
     Rit
    -0.08
    æĺĶ
    -0.08
    unos
    -0.08
    羡
    -0.08
    å¤©åľ°
    -0.08
    çļĭ
    -0.08
     ''.
    -0.08
    POSITIVE LOGITS
    baugh
    0.10
    éĻĶ
    0.09
    bic
    0.09
    åŁŁ
    0.09
    gary
    0.09
    æ·ĸ
    0.09
    sel
    0.09
    èĤļ
    0.09
    uze
    0.09
    AccessException
    0.08
    Activations Density 0.007%

    No Known Activations