© 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. 56388
    Prev
    Next
    INDEX
    Explanations

    heritage breed animal

    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
    ä¸įéĢļ
    -0.10
    .Dispatch
    -0.10
    -cookie
    -0.09
    ç¹ģ
    -0.09
    åīįåIJİ
    -0.09
    å¼ĤæĢ§
    -0.09
    amma
    -0.09
     Mate
    -0.09
    oya
    -0.09
    posição
    -0.09
    POSITIVE LOGITS
    åĽº
    0.10
    èĦIJ
    0.10
    æĪijå¾Ī
    0.09
    bookmark
    0.08
    第ä¸Ģä½į
    0.08
    è¶Ĭ
    0.08
    ä»ĬæĻļ
    0.08
    轶
    0.08
    ivation
    0.08
    çľĭ书
    0.08
    Activations Density 0.073%

    No Known Activations