© 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. 26996
    Prev
    Next
    INDEX
    Explanations

    overwhelmed or daunting situations

    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
    wear
    -0.10
    uce
    -0.10
    ARB
    -0.09
    ıt
    -0.09
    åĬ¡
    -0.09
    gings
    -0.08
    æİĩ
    -0.08
    ÑģÑĤвеннÑĭе
    -0.08
    orate
    -0.08
    ulary
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    ç¨ĭ度
    0.10
    å³Ļ
    0.10
    ä¹ĭä½ľ
    0.09
    å¼Ĭ
    0.09
    åĨ¼
    0.09
    è·ijåİ»
    0.09
     ÙĪجÙĩ
    0.08
    åĩºå±Ģ
    0.08
    åºŀ大çļĦ
    0.08
    Activations Density 0.006%

    No Known Activations