© 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. 58969
    Prev
    Next
    INDEX
    Explanations

    preparation

    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
    åĸ§
    -0.09
    æĢ»ä¼ļ
    -0.09
    ç»Ĭ
    -0.09
    åģ¾
    -0.08
    ÑĤик
    -0.08
    åŁĭ
    -0.08
    verty
    -0.08
    æī§æĦı
    -0.08
     bas
    -0.08
     Wer
    -0.08
    POSITIVE LOGITS
    æŶéĹ´åĨħ
    0.11
    æŶéĹ´ä¸º
    0.10
    æĻĤéĸĵãģĮ
    0.10
    æŶéĹ´åĴĮ
    0.09
    _CONV
    0.09
    ctime
    0.09
    â»
    0.08
    æĻĤéĸĵ
    0.08
    æijĬ
    0.08
    ÑĥÑģÑĤ
    0.08
    Activations Density 0.007%

    No Known Activations