© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    emails dates times

    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
    ä¸Ĭä¸ĸ纪
    -0.10
    ties
    -0.08
    noinspection
    -0.08
    çѵ
    -0.08
    çĩĥ
    -0.08
    4
    -0.07
    0
    -0.07
    2
    -0.07
    æĹ©åľ¨
    -0.07
     gö
    -0.07
    POSITIVE LOGITS
    æĸ¹æīį
    0.09
    æĥħåĨµæĿ¥çľĭ
    0.09
    è¦ģ说
    0.09
    /lic
    0.09
    两个å°ıæŶ
    0.09
    é£İåIJ¹
    0.09
    åĴ¨è¯¢
    0.08
    è§ī
    0.08
    æĭĽçīĮ
    0.08
    å¿ĥèĦıçĹħ
    0.08
    Activations Density 0.079%

    No Known Activations