© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7181
    Prev
    Next
    INDEX
    Explanations

    positive outcomes and states

    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
    èµĮ
    -0.11
    è°¦
    -0.10
     overcrow
    -0.09
    éĹ³
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    ноÑģÑĤей
    -0.08
    idor
    -0.08
     Bul
    -0.08
    æĦŁåĬ¨
    -0.08
     Dec
    -0.08
    POSITIVE LOGITS
    ä¸įåħį
    0.12
     unfavor
    0.09
    ä¸įèī¯
    0.09
    ãģ£ãģ¡ãĤĥ
    0.09
    害
    0.08
    cale
    0.08
     воп
    0.08
    went
    0.08
    pack
    0.08
    æĬ«
    0.08
    Activations Density 0.432%

    No Known Activations