© 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. 57917
    Prev
    Next
    INDEX
    Explanations

    information or service details

    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
    导å¸Ī
    -0.08
    模åĿĹ
    -0.08
    Desk
    -0.08
     Desk
    -0.08
    ä¾Ľ
    -0.07
    çĽĸ
    -0.07
    åĪ»èĭ¦
    -0.07
    urger
    -0.07
     modules
    -0.07
    Observers
    -0.07
    POSITIVE LOGITS
    å¼Ģä¸ļ
    0.12
    å½ĵåľ°çļĦ
    0.12
     Yelp
    0.12
    å½ĵåľ°
    0.11
    èIJ¥ä¸ļ
    0.11
     меÑģÑĤ
    0.10
    æľ¬åľ°
    0.10
     LOCATION
    0.10
    åľ¨å½ĵåľ°
    0.10
    ç»ıèIJ¥æ¨¡å¼ı
    0.10
    Activations Density 0.055%

    No Known Activations