© 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. 1710
    Prev
    Next
    INDEX
    Explanations

    questions or explanations

    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
    äºĮåŃĹ
    -0.08
    cri
    -0.08
    æĢ
    -0.08
    åĽŀæĥ³
    -0.08
    贯穿
    -0.08
     bay
    -0.08
    æ¿Ģæ´»
    -0.08
    åŃĹåı·
    -0.08
    \/
    -0.07
    æ±Ĥå©ļ
    -0.07
    POSITIVE LOGITS
    _UL
    0.09
     Garner
    0.09
    orda
    0.09
    Marks
    0.09
    osten
    0.08
    deen
    0.08
    è¡į
    0.08
    æĤŃ
    0.08
    RAL
    0.08
    nty
    0.08
    Activations Density 0.004%

    No Known Activations