© 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. 38773
    Prev
    Next
    INDEX
    Explanations

    literally

    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
    足以
    -0.10
    èĻ½çĦ¶
    -0.09
    è½»æĺĵ
    -0.08
    笳
    -0.08
    ounder
    -0.08
    ilo
    -0.08
    åıĻ
    -0.08
    ä¸Ģèĩ´
    -0.08
    æĥħèĬĤ
    -0.08
    æĪĸ许
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.12
    çľĭä¸Ģçľĭ
    0.11
    æĦıä¹īä¸Ĭ
    0.11
    mente
    0.10
    -minded
    0.09
    æĶ¾æīĭ
    0.09
    ä»İå°ı
    0.09
    cks
    0.09
    enter
    0.09
    AndView
    0.09
    Activations Density 0.005%

    No Known Activations