© 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. 31266
    Prev
    Next
    INDEX
    Explanations

    for [something]

    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
     Lump
    -0.10
    ิà¸ķ
    -0.09
    iform
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    顺
    -0.09
    èħĬ
    -0.08
    æľºæ²¹
    -0.08
    以çĤº
    -0.08
    ç»´å¥ĩ
    -0.08
    çķ¢
    -0.08
    POSITIVE LOGITS
    è¯ķåĽ¾
    0.09
    示èĮĥ
    0.09
    feit
    0.09
    管çIJĨåĴĮ
    0.08
    åIJij社ä¼ļ
    0.08
    示
    0.08
    é«ĺåĵģè´¨
    0.08
    å¾ĩ
    0.08
    æĺĻ
    0.08
    xdf
    0.08
    Activations Density 0.025%

    No Known Activations