© 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. 31872
    Prev
    Next
    INDEX
    Explanations

    about the

    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
    orny
    -0.09
    ç»İ
    -0.08
    lesia
    -0.08
    rie
    -0.08
    æīĪ
    -0.08
    ispers
    -0.08
     Dak
    -0.08
     ko
    -0.08
    tras
    -0.08
    ldb
    -0.08
    POSITIVE LOGITS
    äºİæѤ
    0.09
    å·¢
    0.09
    é¹ħ
    0.09
    驾
    0.09
     cata
    0.09
    åıĹåĪ°äºĨ
    0.09
    æĻĶ
    0.09
    亡
    0.08
    ä¸ĭåİ»
    0.08
    oleon
    0.08
    Activations Density 0.034%

    No Known Activations