© 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. 61199
    Prev
    Next
    INDEX
    Explanations

    Saint John locations

    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
    èĻı
    -0.10
    ï¸
    -0.10
    ÑĢод
    -0.09
    微信åı·
    -0.09
    æ´²
    -0.09
    nd
    -0.09
    êu
    -0.09
    幺
    -0.09
    apg
    -0.09
    EK
    -0.09
    POSITIVE LOGITS
    举æŃ¢
    0.09
    /tool
    0.08
    èģĮä¸ļæĬĢæľ¯
    0.08
    ../../../
    0.08
    èĩªåľ¨
    0.08
    icals
    0.08
    rys
    0.08
     civ
    0.08
    raud
    0.08
    opsis
    0.08
    Activations Density 0.019%

    No Known Activations