© 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. 19580
    Prev
    Next
    INDEX
    Explanations

    rely upon or on

    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
     friendly
    -0.09
    碣
    -0.09
     Clarkson
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    éļĨéĩį
    -0.08
    çIJĨäºĭéķ¿
    -0.08
    åĸĻ
    -0.08
    æŀ¥
    -0.08
    åĪ©äºİ
    -0.08
    å¾Īå¤ļ
    -0.08
    POSITIVE LOGITS
    alis
    0.08
     Quar
    0.08
    ä¿¡æģ¯å®īåħ¨
    0.08
    åĬ±
    0.08
     information
    0.08
    æľīä»·åĢ¼
    0.08
    .lp
    0.08
     اÙĦبÙĬ
    0.08
    ä»İ严
    0.08
    information
    0.08
    Activations Density 0.005%

    No Known Activations