© 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. 21209
    Prev
    Next
    INDEX
    Explanations

    San Diego State University

    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
    ç»ķ
    -0.09
    æµ·æ·ĢåĮº
    -0.09
    é«ĺåİŁ
    -0.08
     Evel
    -0.08
     gy
    -0.08
    Seattle
    -0.08
    HEST
    -0.08
    èķ²
    -0.08
     hv
    -0.08
    ather
    -0.08
    POSITIVE LOGITS
    æ¹ĺ
    0.10
    æ©ĩ
    0.09
    就好äºĨ
    0.08
    åĴĢ
    0.08
    èĭ¦èĭ¦
    0.08
    éĥ´
    0.08
    æ¡ħ
    0.08
    ×ķ׳×ķ
    0.08
    pics
    0.08
    åĸĤ
    0.08
    Activations Density 0.033%

    No Known Activations