© 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. 30126
    Prev
    Next
    INDEX
    Explanations

    names, often with suffixes

    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
    ç»·
    -0.08
    æĸ½èĤ¥
    -0.08
    ieres
    -0.08
    è¿Ļå¥Ĺ
    -0.08
    ä¸įä¹ħ
    -0.08
    继
    -0.08
    级以ä¸Ĭ
    -0.08
    åĩŃçĿĢ
    -0.08
    河水
    -0.08
    edException
    -0.08
    POSITIVE LOGITS
    igan
    0.10
    oley
    0.08
    _bl
    0.08
    çľ·
    0.08
    æĿ³
    0.08
     Dod
    0.07
    WhatsApp
    0.07
    æ¶Įçİ°
    0.07
    CCA
    0.07
     ÑģекÑĢеÑĤ
    0.07
    Activations Density 0.095%

    No Known Activations