© 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. 32192
    Prev
    Next
    INDEX
    Explanations

    bring, host, celebrated, raises, took

    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
    é¦ĸéĥ½
    -0.09
     Ost
    -0.08
    cest
    -0.08
    ä½ıæīĢ
    -0.08
    主è¦ģä»İäºĭ
    -0.08
    stag
    -0.07
     ÑģовеÑĢ
    -0.07
    å®īåºĨ
    -0.07
    ofire
    -0.07
     quotations
    -0.07
    POSITIVE LOGITS
    æİĩ
    0.10
    procs
    0.10
    åİĨåı²æĤłä¹ħ
    0.09
    à¸Ńม
    0.09
     Biz
    0.09
    èµ·æĿ¥äºĨ
    0.09
    urette
    0.09
    åıĪæľī
    0.09
    æĻļéĹ´
    0.09
    缤纷
    0.09
    Activations Density 0.355%

    No Known Activations