© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7685
    Prev
    Next
    INDEX
    Explanations

    at least [number]

    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
    atif
    -0.09
    éľŃ
    -0.09
    æĺ¯éĿŀ
    -0.09
    æģ»
    -0.09
    åĬ©çIJĨ
    -0.09
    ãĥIJãĥ¬
    -0.09
    éĿ
    -0.08
    çĨĦ
    -0.08
    (Xml
    -0.08
    æıIJé«ĺäºĨ
    -0.08
    POSITIVE LOGITS
    åĵªæĢķæĺ¯
    0.10
    æŁIJç§į
    0.10
    æĹłä¸į
    0.09
    ç¹ģ
    0.09
    æ¯Ľ
    0.09
    ocrates
    0.09
    entry
    0.08
    æĦıä¹īä¸Ĭ
    0.08
     Downing
    0.08
    äºĨèĩªå·±çļĦ
    0.08
    Activations Density 0.081%

    No Known Activations