© 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. 49574
    Prev
    Next
    INDEX
    Explanations

    making it easy/easier/harder/difficult to

    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
     ведÑĮ
    -0.11
    å¤ļåįĬ
    -0.09
    çĵ¶é¢Ī
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    累累
    -0.09
    ä¸įåħį
    -0.08
    ä¼´éļı
    -0.08
    äºĭåħĪ
    -0.08
    èħ°éĥ¨
    -0.08
    dit
    -0.08
    POSITIVE LOGITS
    Rh
    0.10
    çIJĨ解åĴĮ
    0.09
     thợ
    0.09
    urve
    0.08
    ãĥijãĤ¤
    0.08
    Į¨
    0.08
    æݥ纳
    0.08
    inkel
    0.08
    pane
    0.08
    ÑģÑĤи
    0.08
    Activations Density 0.025%

    No Known Activations