© 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. 31101
    Prev
    Next
    INDEX
    Explanations

    high pressure liquid chromatography

    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
    æ´§
    -0.09
    åĿĹ
    -0.09
    æĭ´
    -0.09
    ç¾İè§Ĥ
    -0.09
    æ©IJ
    -0.09
     emanc
    -0.09
    龸æ°Ķ
    -0.08
    æīĵæŃ»
    -0.08
    æĸ¹åIJijçĽĺ
    -0.08
    çľĭäºĨä¸Ģ
    -0.08
    POSITIVE LOGITS
    سÙĬÙĦ
    0.09
    _PRESS
    0.09
    èĭ¦
    0.09
    对æłĩ
    0.09
    çģĮ
    0.09
    аÑģÑĤ
    0.08
    ÃŃch
    0.08
     ìĥĿìĤ°
    0.08
     press
    0.08
    è¿Ŀæ³ķ
    0.08
    Activations Density 0.094%

    No Known Activations