© 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. 52673
    Prev
    Next
    INDEX
    Explanations

    year-round

    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
    å¹³æŶ
    -0.10
    æŃ»åIJİ
    -0.10
    éķ¿è¿ľ
    -0.09
    ort
    -0.09
    æĢ¥éľĢ
    -0.09
    ç»ĪçĶŁ
    -0.09
    æ¯ıå¹´
    -0.08
    oken
    -0.08
    hek
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    POSITIVE LOGITS
    zing
    0.09
    thew
    0.08
    DEX
    0.08
     Petite
    0.08
    æ³³
    0.08
    äºĮæ°§åĮĸ
    0.08
    æĪijéĥ½
    0.08
    ç²¾èĭ±
    0.08
     preparations
    0.08
    imuth
    0.07
    Activations Density 0.006%

    No Known Activations