© 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. 38029
    Prev
    Next
    INDEX
    Explanations

    questions or code snippets after colon

    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
    ices
    -0.09
    çĬĬ
    -0.09
    è¶ģ
    -0.09
    åİī害
    -0.09
    èijŃ
    -0.09
    èĦ±åıij
    -0.08
    尽头
    -0.08
    chie
    -0.08
    èij©
    -0.08
    boa
    -0.08
    POSITIVE LOGITS
    .KeyCode
    0.10
    交æİ¥
    0.10
    éĩİ
    0.10
    åijĹ
    0.10
    æĦĪ
    0.09
    ä¹ŁçŁ¥éģĵ
    0.09
    æµı
    0.09
    VID
    0.09
    åĵªæĢķ
    0.09
    æĺ¥å¤ı
    0.09
    Activations Density 0.210%

    No Known Activations