© 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. 21075
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    íħĶ
    -0.11
    家ä½ı
    -0.10
    è¿ĻåIJį
    -0.10
    驾é©Ń
    -0.10
    èĮ¬
    -0.09
    è¯įæĿ¡
    -0.09
    èĩ´æķ¬
    -0.09
    箧
    -0.08
    æĹłæĥħ
    -0.08
    为æ°ij
    -0.08
    POSITIVE LOGITS
    æ¯ı天
    0.09
    æ´¾
    0.08
    .Annotation
    0.08
     opportunities
    0.08
    HDR
    0.08
     cabin
    0.08
    æ¯ı天éĥ½
    0.08
    ç«ĭå¿Ĺ
    0.08
    ç§ī
    0.08
    tempt
    0.08
    Activations Density 0.054%

    No Known Activations