© 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. 34889
    Prev
    Next
    INDEX
    Explanations

    money and projects

    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
    å¹½
    -0.10
    åijĬè¯īä»ĸ
    -0.09
    èħ¹
    -0.09
    åijĬè¯ī她
    -0.09
    èĥ½å¾ĹåĪ°
    -0.09
    æľįåĬ¡æľºæŀĦ
    -0.09
    ä¾Ŀæīĺ
    -0.09
     Rafael
    -0.09
    å¨ģåĬĽ
    -0.09
    éĢŀ
    -0.08
    POSITIVE LOGITS
    iri
    0.11
    è´Łæĭħ
    0.11
    irs
    0.10
    主åĬ¨
    0.10
    ä¹īåĬ¡
    0.10
    æĮº
    0.09
    派人
    0.09
    æįIJ
    0.09
    åħ³å¿ĥ
    0.09
    äºĨä¸įå°ij
    0.09
    Activations Density 0.205%

    No Known Activations