© 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. 17118
    Prev
    Next
    INDEX
    Explanations

    former, past, present

    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
    æĽ©
    -0.10
    娣
    -0.09
    çı©
    -0.09
    æijŃ
    -0.09
    亲å±ŀ
    -0.09
     aver
    -0.09
    ìŀĶ
    -0.09
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.08
    é¥
    -0.08
    èµ°å»Ĭ
    -0.08
    POSITIVE LOGITS
    第ä¸ĢæĿ¡
    0.09
    /current
    0.09
    æĹłä¸į
    0.09
    elo
    0.08
    俦
    0.08
    aroo
    0.08
    èĢĮåIJİ
    0.08
    éľĩ
    0.08
     cust
    0.08
    åı¯æĥ³
    0.08
    Activations Density 0.035%

    No Known Activations