© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    again from or within

    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
    ä¸Ģé¡¿
    -0.10
    åĹij
    -0.09
    å½ĵä¹ĭæĹłæĦ§
    -0.09
    楼ä¸Ĭ
    -0.09
    æĿ¥çļĦ
    -0.09
    ctic
    -0.08
    åħ¨å¤©
    -0.08
    åIJĮæŶè¿ĺ
    -0.08
    å¾ľ
    -0.08
    çĦķåıij
    -0.08
    POSITIVE LOGITS
    åĸĦæĦı
    0.09
    åĤ¬åĮĸ
    0.09
    个å°ı
    0.09
    ãģ¹ãģį
    0.08
    бл
    0.08
    ãģ£ãģįãĤĬ
    0.08
    è¢ĸ
    0.08
    æıIJéĨĴ
    0.08
    linky
    0.08
     cheeses
    0.08
    Activations Density 0.033%

    No Known Activations