© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8624
    Prev
    Next
    INDEX
    Explanations

    sensations and feelings

    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
    åŀ¢
    -0.11
    пиÑĤ
    -0.10
    积
    -0.10
    å±ķçİ°åĩº
    -0.09
    ç¬Ļ
    -0.09
    ç§ĭ
    -0.09
    mus
    -0.09
    ë²Į
    -0.09
     kald
    -0.09
    SetActive
    -0.08
    POSITIVE LOGITS
    éĻĮçĶŁ
    0.09
    rush
    0.08
     Dell
    0.08
    æ»ĭåij³
    0.08
    æľªå©ļ
    0.08
    æģ¯
    0.08
    leck
    0.08
    пол
    0.08
     PHY
    0.08
     Getty
    0.07
    Activations Density 0.068%

    No Known Activations