© 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. 2245
    Prev
    Next
    INDEX
    Explanations

    prices, rates, and fares

    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
     Ves
    -0.12
    人æ°Ķ
    -0.09
    è¾¾åĪ°äºĨ
    -0.09
     Keller
    -0.08
    æĮijæĪĺ
    -0.08
     challenge
    -0.08
    论
    -0.08
    á»į
    -0.08
    ضاء
    -0.08
     harmonic
    -0.08
    POSITIVE LOGITS
    ingo
    0.11
    é«ĺåĵģè´¨
    0.10
    éŀł
    0.09
    è´¨éĩıåĴĮ
    0.09
    åıĺå¾ĹæĽ´
    0.09
    мÑĭÑģл
    0.09
    便æ°ij
    0.09
    æľįåĬ¡è´¨éĩı
    0.09
    åĤ¬
    0.09
     ÑĨенÑĭ
    0.09
    Activations Density 0.085%

    No Known Activations