© 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. 34220
    Prev
    Next
    INDEX
    Explanations

    aphasia, edentulous, euhydrated, anovulatory

    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
    .land
    -0.09
    ä¸įä¸Ģæł·çļĦ
    -0.08
    ences
    -0.08
    iba
    -0.08
    ipples
    -0.08
    dsl
    -0.08
    å¹¿æ³ĽçļĦ
    -0.08
    ç§ĭ
    -0.08
    ä¸ĢæŃ¥
    -0.08
    -ranked
    -0.07
    POSITIVE LOGITS
    ism
    0.12
    æŀ§
    0.11
    æĪĸå¤ļ
    0.10
    ISM
    0.10
    изм
    0.10
    isch
    0.09
    讳
    0.09
    主ä¹īèĢħ
    0.09
    atism
    0.09
    isia
    0.09
    Activations Density 0.578%

    No Known Activations