© 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. 51165
    Prev
    Next
    INDEX
    Explanations

    fall into

    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
    enance
    -0.11
    çĿĢåĬĽ
    -0.09
    Ùĩب
    -0.09
    emporary
    -0.09
    æ´ģçĻ½
    -0.08
    ç¯Ļ
    -0.08
    cep
    -0.08
    .Body
    -0.08
    imentos
    -0.08
    è¿ĩçļĦ
    -0.08
    POSITIVE LOGITS
    çľ¼éķľ
    0.10
    ç©´
    0.10
    æ²Ł
    0.10
    пÑĢоÑģ
    0.09
    .Generated
    0.09
    åıªçŁ¥éģĵ
    0.09
    æ´»
    0.09
    lap
    0.08
    ä¸Ģç§į
    0.08
     bre
    0.08
    Activations Density 0.010%

    No Known Activations