© 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. 39579
    Prev
    Next
    INDEX
    Explanations

    sports equipment and players

    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
    温æ³ī
    -0.08
     Poker
    -0.08
    EDIA
    -0.08
    éĴĵé±¼
    -0.08
    dbuf
    -0.08
    èĪ¶
    -0.08
    æĶ¯æĮģåĬĽåº¦
    -0.08
     Firearms
    -0.08
    éĴ
    -0.08
    Fully
    -0.08
    POSITIVE LOGITS
    éĺŁåijĺ
    0.13
    ä¼łçIJĥ
    0.12
    éĺŁåijĺ们
    0.12
    åīįéĶĭ
    0.11
    çĬ¯è§Ħ
    0.11
    ç»ĥä¹ł
    0.10
    é¢Ħå¤ĩ
    0.10
    éĺŁåıĭ
    0.09
    åľºä¸Ĭ
    0.09
    çIJĥåijĺ
    0.09
    Activations Density 0.138%

    No Known Activations