© 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. 2749
    Prev
    Next
    INDEX
    Explanations

    people who

    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
    人éĢī
    -0.10
    é£Ĵ
    -0.10
    åį§
    -0.10
    人æķ°
    -0.09
    æŶèĬĤ
    -0.09
    åı¦æľī
    -0.09
    好è¯Ħ
    -0.09
    å¼ķæĿ¥
    -0.08
    诤
    -0.08
    èĢIJ
    -0.08
    POSITIVE LOGITS
    Dies
    0.09
    迹
    0.09
    oj
    0.08
     Interpret
    0.08
    rome
    0.08
    ajes
    0.08
    à¹Ħà¸Ĥ
    0.08
    /entity
    0.08
     Redistributions
    0.08
    duino
    0.08
    Activations Density 0.178%

    No Known Activations