© 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. 10686
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    åħļçļĦ建设
    -0.10
    è¡¥é½IJ
    -0.09
    ponsible
    -0.09
    Reflect
    -0.09
    пи
    -0.09
    acen
    -0.09
    æĦĢ
    -0.09
    æĺ¯ä¸Ģ项
    -0.08
     Reflect
    -0.08
    以åħ¶
    -0.08
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.09
     Bermuda
    0.09
    éĢīæĭ©äºĨ
    0.08
    åĴĮåıijå±ķ
    0.08
    åı¯ä»¥éĢīæĭ©
    0.08
    /remove
    0.08
    æĸ°äº¬
    0.08
     opening
    0.08
    åIJĮæľŁ
    0.08
    å°ıäºĭ
    0.08
    Activations Density 0.132%

    No Known Activations