© 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. 50058
    Prev
    Next
    INDEX
    Explanations

    question marks and what follows

    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
    VICE
    -0.10
    uju
    -0.09
    éĺ¶çº§
    -0.09
     zwar
    -0.09
    ripe
    -0.09
    vice
    -0.09
    baugh
    -0.09
    most
    -0.09
    جاز
    -0.08
    جاÙħ
    -0.08
    POSITIVE LOGITS
    oot
    0.10
    ï¸ı
    0.09
    osoph
    0.09
    ØŁ
    0.08
    ever
    0.08
    ï¼Ł
    0.08
    äºŃ
    0.08
    oned
    0.08
    æ¯Ĥ
    0.08
    ?.
    0.08
    Activations Density 0.306%

    No Known Activations