© 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. 19368
    Prev
    Next
    INDEX
    Explanations

    law or

    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
    out
    -0.10
    ạnh
    -0.09
    peak
    -0.09
    1
    -0.08
    plane
    -0.08
    é«ĺä»·
    -0.08
    pars
    -0.08
    oby
    -0.08
    辩
    -0.08
    /ref
    -0.08
    POSITIVE LOGITS
    éĩįè§Ĩ
    0.11
    æľºåħ³
    0.11
    ä¸įå¾Ĺ转载
    0.10
     sovere
    0.10
    å¾Īå¤ļäºĭæĥħ
    0.10
    èķ¤
    0.10
    çĴİ
    0.10
    åIJĥå¾Ĺ
    0.09
    æ¹ĸåĮº
    0.09
    éĺ²çĽĹ
    0.09
    Activations Density 0.031%

    No Known Activations