© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50892
    Prev
    Next
    INDEX
    Explanations

    chocolate and cream confectionery

    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
    ủng
    -0.09
    arde
    -0.09
    æĹĮ
    -0.09
    妻
    -0.09
    æĹĹ
    -0.09
    é¹°
    -0.09
    ä¹łæĥ¯äºĨ
    -0.09
    è°ĥçIJĨ
    -0.08
    _macros
    -0.08
    د
    -0.08
    POSITIVE LOGITS
    çİĭåĽ½
    0.12
    符
    0.09
    ram
    0.09
    æŁ¬
    0.09
    ä½¥
    0.08
    ikes
    0.08
    åĮł
    0.08
    æ¾Ħ
    0.08
    æļ´åĬĽ
    0.08
    åļ·
    0.08
    Activations Density 0.008%

    No Known Activations