© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51576
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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
    heck
    -0.10
    ston
    -0.09
    佬
    -0.08
    rie
    -0.08
     нап
    -0.08
    ä¿Ĺ称
    -0.08
    ane
    -0.08
    oves
    -0.08
    uin
    -0.08
    ouse
    -0.08
    POSITIVE LOGITS
    ä¸įä¸Ģå®ļ
    0.11
     обÑĢазом
    0.11
    æĦıä¹īä¸ĬçļĦ
    0.10
    ski
    0.10
    æĦıä¹īä¸Ĭ
    0.10
    æĺ¯åľ¨
    0.09
    åľ°è¯´
    0.09
    ìĶ©
    0.09
    à¸Ĺà¸ĺ
    0.09
    itty
    0.09
    Activations Density 0.008%

    No Known Activations