© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19972
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities like 2, 5, 3

    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
    ieri
    -0.09
    è¹Ĭ
    -0.08
     нÑĥж
    -0.08
     Hyde
    -0.08
    寸
    -0.08
    èĮĦåŃIJ
    -0.08
    æŃ»åİ»
    -0.08
     Zub
    -0.08
    loff
    -0.08
    è¾ĺ
    -0.08
    POSITIVE LOGITS
    大æ¦Ĥæĺ¯
    0.17
    ä¹Łè®¸æĺ¯
    0.14
     somewhere
    0.13
    æĪijè®°å¾Ĺ
    0.12
     maybe
    0.12
    確ãģĭ
    0.11
    maybe
    0.11
    大æ¦Ĥ
    0.10
    æŁIJç§į
    0.10
    ä¸Ģå®ļæĺ¯
    0.10
    Activations Density 0.075%

    No Known Activations