© 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. 17940
    Prev
    Next
    INDEX
    Explanations

    detecting or sensing

    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
    andin
    -0.10
    ди
    -0.10
     Mahar
    -0.09
    ÑģÑĥ
    -0.09
    çĨĻ
    -0.09
    åħ¨æĹ¥
    -0.09
    ika
    -0.09
    aul
    -0.08
    iglia
    -0.08
    cken
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¸Ŀ
    0.13
    ä¸Ŀä¸Ŀ
    0.12
    ä¸ĢèĤ¡
    0.11
    åķĨæľº
    0.11
    ä¸įå®ī
    0.10
    æ°Ķæ°Ľ
    0.10
    å¯Łè§ī
    0.10
    æĦŁè§īåĪ°
    0.10
    é¹ľ
    0.10
    ivet
    0.09
    Activations Density 0.016%

    No Known Activations