© 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. 11263
    Prev
    Next
    INDEX
    Explanations

    taught Hebrew

    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
    以èī²
    -0.12
    çĶij
    -0.10
    åIJ¦è®¤
    -0.09
    è´´
    -0.09
    以èī²åĪĹ
    -0.09
    幸ç¦ı
    -0.09
    çī©åĵģ
    -0.09
    .GetObject
    -0.08
    åij¼åĶ¤
    -0.08
    é¢ł
    -0.08
    POSITIVE LOGITS
    çĤĴä½ľ
    0.10
    åŀĤ
    0.09
    åĪ©çĽĬ
    0.08
    主å¸Ń
    0.08
    urf
    0.08
    æ´ĭæ´ĭ
    0.08
    åģıè¿ľ
    0.08
    æ»Ĥ
    0.08
    æĪIJçĨŁ
    0.08
     ÑĤоÑĢ
    0.08
    Activations Density 0.022%

    No Known Activations