© 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. 35372
    Prev
    Next
    INDEX
    Explanations

    to you

    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
    å¾Īåĸľæ¬¢
    -0.10
    åŀĤ
    -0.10
    ä»ĸæĽ¾
    -0.10
    å¯Ł
    -0.10
    ä¸ĭæīĭ
    -0.10
    ulton
    -0.10
    为ä»Ģä¹Īä¸į
    -0.10
    annt
    -0.09
    ighted
    -0.09
    annis
    -0.09
    POSITIVE LOGITS
    åľ°å½¢
    0.09
    æĬĬä½ł
    0.08
    带çĿĢ
    0.07
    ãĥĮ
    0.07
    åį³ä¾¿
    0.07
    åĪĨåĪ«
    0.07
     tell
    0.07
    puter
    0.07
    ialog
    0.07
    å¡«
    0.07
    Activations Density 0.022%

    No Known Activations