© 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. 34038
    Prev
    Next
    INDEX
    Explanations

    indicates provision or future occurrence

    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
    饶
    -0.10
    IFIER
    -0.10
     spoiled
    -0.09
    /or
    -0.09
    è°Ł
    -0.09
    pill
    -0.09
    anness
    -0.08
    мÑı
    -0.08
    çŀ½
    -0.08
     Bou
    -0.08
    POSITIVE LOGITS
    éļ¾æĢª
    0.09
     means
    0.09
    社ä¼ļ稳å®ļ
    0.09
    æ¸Ĺ
    0.09
    -pad
    0.09
     observable
    0.08
    æ´ŀ
    0.08
     happen
    0.08
    ä¹Łå°±æĺ¯
    0.08
    ä½Ĩå®ĥ
    0.08
    Activations Density 0.209%

    No Known Activations