© 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. 50036
    Prev
    Next
    INDEX
    Explanations

    where followed by clauses

    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
     Dunn
    -0.10
    ä»įåľ¨
    -0.08
    æĺ¯ä¸Ģ项
    -0.08
    ä¸ĭæīĭ
    -0.08
    anga
    -0.08
    emu
    -0.08
    æ¡¢
    -0.08
    à¸ģระ
    -0.08
    [obj
    -0.08
    otti
    -0.08
    POSITIVE LOGITS
    æĹ¢è¦ģ
    0.10
     POSSIBILITY
    0.10
    èįĴ
    0.09
    ä»Ģä¹Īéĥ½
    0.08
    ç§ĺ
    0.08
    è¦ģä¹Ī
    0.08
    atl
    0.08
    orama
    0.08
    ä¸įåĩº
    0.08
    åį°è±¡
    0.08
    Activations Density 0.105%

    No Known Activations