© 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. 49934
    Prev
    Next
    INDEX
    Explanations

    reactions and criticisms

    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
    åĵ¨
    -0.09
     أج
    -0.09
    åľ°å½¢
    -0.09
    èĤĦ
    -0.09
    EDIUM
    -0.08
    STRUCTOR
    -0.08
    archy
    -0.08
    ãĦ±
    -0.08
    Ñħодим
    -0.08
     erw
    -0.08
    POSITIVE LOGITS
    åķĥ
    0.10
    å¼Ľ
    0.09
    æģ¯
    0.09
    edd
    0.09
    ä½Ĩä¹Ł
    0.09
    æĹłæķ°
    0.09
    åİ
    0.08
    款
    0.08
    æĪIJ为ä¸ŃåĽ½
    0.08
     polar
    0.08
    Activations Density 0.240%

    No Known Activations