© 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. 63508
    Prev
    Next
    INDEX
    Explanations

    doubt, know, sure

    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
    zel
    -0.09
    ç½ķè§ģ
    -0.09
    plx
    -0.09
    ãģĦãĤī
    -0.08
    ãģªãģ®ãģ«
    -0.08
    rus
    -0.08
    intl
    -0.08
    éĿŀ常æĺİæĺ¾
    -0.08
    éĽģ
    -0.08
    Ø¡
    -0.08
    POSITIVE LOGITS
    æĥ³å¿ħ
    0.14
    èĤ¯å®ļä¼ļ
    0.12
    likely
    0.12
     likely
    0.12
    æĹłçĸij
    0.11
    çĽ¸ä¿¡
    0.11
    èĤ¯å®ļæĺ¯
    0.10
    å¿ħå°Ĩ
    0.10
    probably
    0.10
    ãģįãģ£ãģ¨
    0.10
    Activations Density 0.038%

    No Known Activations