© 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. 20256
    Prev
    Next
    INDEX
    Explanations

    at least followed by quantifier or modifier

    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
    éĵ©
    -0.10
    ä»İæł¹æľ¬
    -0.10
    å§Ŀ
    -0.09
    ãģĿãĤĤãģĿãĤĤ
    -0.09
    们
    -0.09
    æĤ¨çļĦåŃ©åŃIJ
    -0.09
    athed
    -0.09
    .Ver
    -0.09
    æī¾åĽŀ
    -0.09
    .setVertical
    -0.09
    POSITIVE LOGITS
     partially
    0.10
    èµ·çłģ
    0.09
    æľīä¸Ģä½į
    0.09
    åĨĴ
    0.09
    ly
    0.09
     conceptual
    0.08
    åĩĨ
    0.08
    ä¸Ģå®ļç¨ĭ度
    0.08
    æĺ¯åľ¨
    0.08
    åIJĬ
    0.08
    Activations Density 0.017%

    No Known Activations