© 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. 20342
    Prev
    Next
    INDEX
    Explanations

    work and fun

    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
    çĻ»
    -0.09
    tré
    -0.08
     recurs
    -0.08
    oped
    -0.08
    (NS
    -0.08
    é½Ĭ
    -0.08
    èµĭäºĪ
    -0.08
     Clem
    -0.08
    å®ģ
    -0.08
    еÑĤе
    -0.08
    POSITIVE LOGITS
    ç¦ģåĮº
    0.10
    ç²¾åĵģ
    0.10
    elves
    0.10
    æĢ§å¼º
    0.10
     باÙĦÙĨسبة
    0.10
    ä¸Ńå°ıåŀĭ
    0.09
    iban
    0.09
    eline
    0.09
    äºļ马
    0.09
    ä¸Ńåħ±
    0.09
    Activations Density 0.099%

    No Known Activations