© 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. 1658
    Prev
    Next
    INDEX
    Explanations

    not 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
    åĪ°åºķ
    -0.09
    å¤Ł
    -0.09
    ä¸įè¦ģ太
    -0.08
    æĥ³èµ·æĿ¥
    -0.08
    èµ·æĿ¥
    -0.08
    /fixtures
    -0.08
    æķ°çłģ
    -0.08
    è§Ĵèī²
    -0.08
    .apps
    -0.08
    ä»įçĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
    ä¸Ŀä¸Ŀ
    0.10
    æĬĺ
    0.09
    DMIN
    0.09
    çĸ«æĥħå½±åĵį
    0.09
    åIJ¹
    0.09
    uyết
    0.09
    è½»æĺĵ
    0.09
    onia
    0.09
    woord
    0.09
    å¼łæī¬
    0.09
    Activations Density 0.009%

    No Known Activations