© 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. 33914
    Prev
    Next
    INDEX
    Explanations

    although / while

    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
    china
    -0.10
    åħ¸åŀĭçļĦ
    -0.10
    çĻ½èī²çļĦ
    -0.09
    åįĹå±±
    -0.09
    etsk
    -0.09
    æł¹æį®èĩªå·±
    -0.09
    为äºĨ让
    -0.09
    è¿Ļæł·çļĦ
    -0.09
    OTO
    -0.09
     ÑģÑĭн
    -0.09
    POSITIVE LOGITS
    æ±Ĺ
    0.09
    fds
    0.08
    BuilderFactory
    0.08
     Ivory
    0.08
    æ·Į
    0.08
    hip
    0.08
    tra
    0.08
    å¼ĤæĢ§
    0.08
    ä¸Ģ次次
    0.08
    æľī个
    0.07
    Activations Density 0.022%

    No Known Activations