© 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. 38721
    Prev
    Next
    INDEX
    Explanations

    family and relatives

    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
    两ä½į
    -0.09
    æŶèĬĤ
    -0.09
    ailed
    -0.08
    æĭ¾
    -0.08
    avar
    -0.08
    croft
    -0.08
    综
    -0.08
    讽åĪº
    -0.08
    æ¿ij
    -0.08
     Gä
    -0.08
    POSITIVE LOGITS
    ä¸Ńå°ıåŀĭ
    0.10
    èĤ¯
    0.10
    æµĩ
    0.09
    ady
    0.09
    apus
    0.09
    inth
    0.09
    åĻľ
    0.09
    SCO
    0.09
    ien
    0.08
    zin
    0.08
    Activations Density 0.033%

    No Known Activations