© 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. 29804
    Prev
    Next
    INDEX
    Explanations

    legal actions stopping or recovering funds

    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
    å°ıäºĭ
    -0.10
    大夫
    -0.09
    legalArgumentException
    -0.09
    _EXPECT
    -0.09
     Merkel
    -0.09
    бол
    -0.09
    ).__
    -0.09
    ighter
    -0.09
    .nlm
    -0.09
    zell
    -0.09
    POSITIVE LOGITS
     ìķŀìľ¼ë¡ľ
    0.10
    æĬĬ她
    0.09
    ä»ĬåIJİ
    0.08
    èĹIJ
    0.08
    èķº
    0.08
    æķ´æĶ¹æݪæĸ½
    0.08
    éĩijéĻµ
    0.08
    ä¸ĭ次
    0.08
     interference
    0.08
    继ç»Ń
    0.08
    Activations Density 0.092%

    No Known Activations