© 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. 30459
    Prev
    Next
    INDEX
    Explanations

    critical thinking

    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
    åľ¨çİ°åľº
    -0.09
     cascade
    -0.08
     med
    -0.08
    æģ¢å¤į
    -0.08
    æ®ĭ
    -0.08
    æĪ·
    -0.08
    æѦ
    -0.08
    æŀ¶æŀĦ
    -0.08
    å·¾
    -0.08
    ä¸ĩåIJį
    -0.08
    POSITIVE LOGITS
    æİ¥åħ¥
    0.11
    ç´łåħ»
    0.10
    anton
    0.09
    æijĪ
    0.09
     sources
    0.09
     ÑģамоÑģÑĤоÑı
    0.08
     Bennett
    0.08
    ä¸įèī¯ä¿¡æģ¯
    0.08
    åĤį
    0.08
    ç¿©
    0.08
    Activations Density 0.060%

    No Known Activations