© 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. 32915
    Prev
    Next
    INDEX
    Explanations

    do to

    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
    ä»İäºĭ
    -0.09
    جاÙĨ
    -0.09
    ä»Ģä¹ĪåİŁåĽł
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    pitch
    -0.09
    æľīä½ķ
    -0.08
    åij±
    -0.08
    cratch
    -0.08
    ium
    -0.08
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.08
    POSITIVE LOGITS
    иÑĤелÑĮн
    0.09
    设æĥ³
    0.09
    recht
    0.09
    иÑĤел
    0.08
    TabPage
    0.08
     Ñĩа
    0.08
    å¯ĵ
    0.08
    ÑĤов
    0.08
    xor
    0.08
    æ¹į
    0.08
    Activations Density 0.076%

    No Known Activations