© 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. 52362
    Prev
    Next
    INDEX
    Explanations

    each/every + singular noun

    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
    åİĨåı²ä¸Ĭ
    -0.10
    è¿ľå¤Ħ
    -0.10
    é»ĺ
    -0.10
    å»ºåĽ½
    -0.09
    _secret
    -0.09
    å½ĵåľ°çļĦ
    -0.08
    _exe
    -0.08
    å¼¼
    -0.08
    adem
    -0.08
    è¿ĻéĩĮçļĦ
    -0.08
    POSITIVE LOGITS
    æ¯ıä¸Ģ个
    0.11
    æ¯ıä¸Ģä½į
    0.10
    潦
    0.10
    ç»ĨèĬĤ
    0.09
    rx
    0.09
    æ¯ıä½į
    0.09
    ilder
    0.09
    èĽĽ
    0.09
    enstein
    0.09
    egree
    0.08
    Activations Density 0.031%

    No Known Activations