© 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. 39117
    Prev
    Next
    INDEX
    Explanations

    reasons for

    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
    usters
    -0.10
    æĿĥ
    -0.10
    agn
    -0.09
    Boot
    -0.09
    å«Ķ
    -0.09
    éħļ
    -0.09
    å¿ĥ缮ä¸Ń
    -0.09
     Boot
    -0.08
    _boot
    -0.08
    é¤IJ
    -0.08
    POSITIVE LOGITS
    çIJĨçĶ±
    0.24
    çļĦçIJĨçĶ±
    0.23
     reasons
    0.21
     reason
    0.17
     Reasons
    0.17
    为ä»Ģä¹Īè¦ģ
    0.15
     why
    0.14
     ìĿ´ìľł
    0.14
    åĬ¨æľº
    0.14
    reason
    0.14
    Activations Density 0.050%

    No Known Activations