© 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. 53401
    Prev
    Next
    INDEX
    Explanations

    logical structure or order

    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
    é¢ĦåijĬ
    -0.09
    eln
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    emaker
    -0.08
    çijķ
    -0.08
     Sha
    -0.08
    å¼ıçļĦ
    -0.08
    æ³¢çī¹
    -0.08
    _SHA
    -0.08
    artz
    -0.08
    POSITIVE LOGITS
    sWith
    0.10
    åĮºåĿĹ
    0.09
    åıĪ好
    0.09
    ities
    0.09
    ity
    0.09
    ENSE
    0.09
    æĶ¾æīĭ
    0.09
    Logical
    0.09
    åĪĨåĮº
    0.09
    tep
    0.08
    Activations Density 0.014%

    No Known Activations