© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52622
    Prev
    Next
    INDEX
    Explanations

    "the" followed by length/name/present

    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
    代è¨Ģ
    -0.09
    å®¶åĸ»æĪ·æĻĵ
    -0.08
    panse
    -0.08
    èĥł
    -0.08
    å®Įç»ĵ
    -0.08
     fam
    -0.08
    æ¶²ä½ĵ
    -0.07
    ä¸ŃåĽ½æĶ¿åºľ
    -0.07
    ä¸ŃåĽ½å¤§éĻĨ
    -0.07
    主ä¸ļ
    -0.07
    POSITIVE LOGITS
    åīįè¿°
    0.09
     ЮÑĢ
    0.09
     Shirley
    0.08
    快讯
    0.08
    示èĮĥåŁºåľ°
    0.08
    dex
    0.08
    åĴ¨è¯¢æľįåĬ¡
    0.08
    æĦ£
    0.08
    管家
    0.08
    ircle
    0.08
    Activations Density 1.949%

    No Known Activations