© 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. 5219
    Prev
    Next
    INDEX
    Explanations

    underlying concepts or cornerstones

    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
    èµ
    -0.09
    å·¥
    -0.09
    âĢ
    -0.08
     اÙĦÙħÙĦ
    -0.08
    ync
    -0.08
    âĢĮ
    -0.08
    æļ´éľ²
    -0.08
    å¦į
    -0.08
    è±ģ
    -0.07
    olo
    -0.07
    POSITIVE LOGITS
     basis
    0.19
    basis
    0.17
    _basis
    0.15
     Basis
    0.14
     оÑģнове
    0.14
     BASIS
    0.13
    æł¹åºķ
    0.13
    åŁºç¡Ģä¸Ĭ
    0.12
    ä¸ºåŁºç¡Ģ
    0.12
     underlying
    0.12
    Activations Density 0.064%

    No Known Activations