© 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. 52815
    Prev
    Next
    INDEX
    Explanations

    dystopian totalitarianism

    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
    indle
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    yla
    -0.09
     Sao
    -0.09
    ä¿ij
    -0.08
    PLAIN
    -0.08
    ãģĵãģ¨ãģĮãģĤãĤĬãģ¾ãģĻ
    -0.08
     Goodman
    -0.08
    ouri
    -0.08
    ç¾Ķ
    -0.08
    POSITIVE LOGITS
    stem
    0.09
    iams
    0.08
    å¿Ĺ强
    0.08
    ariat
    0.08
    è¯Ŀ说
    0.08
    ÑģÑĤи
    0.08
    оз
    0.08
    -leaning
    0.08
    TF
    0.08
    adius
    0.08
    Activations Density 0.010%

    No Known Activations