© 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. 57701
    Prev
    Next
    INDEX
    Explanations

    consolidate or combining

    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
    ãĥĥãĥĦ
    -0.10
    çļĦçľ¼çĿĽ
    -0.09
    ูà¸ģ
    -0.09
    áĥ®
    -0.09
    æĸ¡
    -0.08
    asa
    -0.08
    转åĮĸ
    -0.08
     ÐľÐ°
    -0.08
    rics
    -0.08
    gings
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.14
    èµĦæºIJæķ´åIJĪ
    0.10
    åī©ä¸ĭ
    0.09
    èĮ¬
    0.08
    è¿ŁåĪ°
    0.08
    elling
    0.08
     Rubber
    0.08
     деÑıÑĤелÑĮноÑģÑĤи
    0.08
    éĺµåľ°
    0.08
    产åĮº
    0.08
    Activations Density 0.072%

    No Known Activations