© 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. 19962
    Prev
    Next
    INDEX
    Explanations

    invention relates 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
    upported
    -0.10
    æľ¬åľºæ¯ĶèµĽ
    -0.09
    pollo
    -0.09
    VISIBLE
    -0.09
    æ³ķåħ°
    -0.09
    .Localization
    -0.09
    èĤ¡æĿĥæĬķèµĦ
    -0.09
    ä¸ĭä¸Ģç¯ĩ
    -0.09
    senal
    -0.09
    åIJĪèµĦ
    -0.09
    POSITIVE LOGITS
    ç»ĥä¹ł
    0.15
    æ¼Ķä¹ł
    0.14
    æ¼Ķç»ĥ
    0.14
    ç»ĥ
    0.12
    æµĭè¯ķ
    0.12
     test
    0.12
    è®Ńç»ĥ
    0.12
     testing
    0.11
    è§Ĥæij©
    0.11
    ãĥĨãĤ¹ãĥĪ
    0.10
    Activations Density 0.063%

    No Known Activations