© 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. 55626
    Prev
    Next
    INDEX
    Explanations

    occupies

    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
    egis
    -0.09
    ream
    -0.09
     cityName
    -0.09
    orm
    -0.08
    ẩ
    -0.08
    ä¿Ŀéļľ
    -0.08
    ë°¤
    -0.08
    اÙĨÙĬ
    -0.08
    venture
    -0.08
    _axes
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.10
    ç«ĭåľº
    0.09
     orb
    0.09
    ä¹ĭåĬ¿
    0.09
    伶
    0.08
    çĦ¶æĺ¯
    0.08
    缸å½ĵ
    0.08
    ulist
    0.08
    æŁľåı°
    0.08
    jong
    0.08
    Activations Density 0.019%

    No Known Activations