© 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. 50117
    Prev
    Next
    INDEX
    Explanations

    again

    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
    axter
    -0.09
    å¼Ģæľº
    -0.09
    .Alter
    -0.09
    ç¹ģ
    -0.09
    prite
    -0.08
    eren
    -0.08
    æĪIJç«ĭ
    -0.08
    ambi
    -0.08
    anus
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    飬
    0.11
    强è°ĥ
    0.11
    第ä¸ī次
    0.10
    çĽ¸ä¿¡å¤§å®¶
    0.09
    åĽ½å®¶æĪĺçķ¥
    0.09
    ä»ĭ
    0.09
     Petite
    0.09
    è´Ŀå°Ķ
    0.09
    éĸ
    0.09
     Unsigned
    0.08
    Activations Density 0.009%

    No Known Activations