© 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. 38426
    Prev
    Next
    INDEX
    Explanations

    every or any

    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
    enis
    -0.09
    ichel
    -0.09
    ãģĵãģĿ
    -0.09
    å°½éĩı
    -0.09
    éĥ¨åĪĨåľ°åĮº
    -0.08
    æ³ĵ
    -0.08
    æļĤæŶ
    -0.08
    ervo
    -0.08
    éĿŀ常çļĦ
    -0.08
     rer
    -0.08
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.11
    åĨµ
    0.11
    pliers
    0.09
    人éĥ½
    0.09
    èĥ½æ»¡è¶³
    0.09
    éĽĨä¸Ńåľ¨
    0.09
    ór
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    ä¸īåĽĽ
    0.09
    è¿ĺæľīä»Ģä¹Ī
    0.09
    Activations Density 0.018%

    No Known Activations