© 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. 61124
    Prev
    Next
    INDEX
    Explanations

    diffraction, interference, structures, spatial

    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
    éļıæīĭ
    -0.10
    æ¶Īè´¹
    -0.10
    bull
    -0.09
    _RESP
    -0.08
    æįİ
    -0.08
    leh
    -0.08
    SPI
    -0.08
    æĨĭ
    -0.08
    俱ä¹IJ
    -0.08
    æ¶Īè²»
    -0.08
    POSITIVE LOGITS
    è¶Ĭ
    0.10
    纹
    0.09
    è±Ĩçĵ£
    0.09
    tat
    0.09
     SMART
    0.09
     jar
    0.08
    alar
    0.08
    ç¼ĸç»ĩ
    0.08
    æ³ķå®ļ
    0.08
    è¯Ŀåī§
    0.08
    Activations Density 0.199%

    No Known Activations