© 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. 10457
    Prev
    Next
    INDEX
    Explanations

    Hebrew origin and language

    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
    amous
    -0.10
    arak
    -0.09
    adic
    -0.09
    åīįåĪĹ
    -0.09
    mercial
    -0.08
    å¿ĥ头
    -0.08
    adays
    -0.08
    èĮĥ
    -0.08
    andon
    -0.08
    ue
    -0.08
    POSITIVE LOGITS
    ãģªãĤĬãģ¾ãģĽãĤĵ
    0.10
    滢
    0.09
    æľīæľŁ
    0.09
    auty
    0.09
    å°Ŀ
    0.09
    é¢Ĩè·ij
    0.09
    ä¹ĭå¿ĥ
    0.09
    -speaking
    0.08
    etr
    0.08
    é¢Ļ
    0.08
    Activations Density 0.005%

    No Known Activations