© 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. 27686
    Prev
    Next
    INDEX
    Explanations

    evidence suggests that

    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
    ç»ĪçĶŁ
    -0.12
    èªķ
    -0.10
    å½ĵåľ°çļĦ
    -0.10
    è¯ŀ
    -0.10
    åĽļ
    -0.09
    æ²¼
    -0.09
    å®ŀåľ¨æĺ¯å¤ª
    -0.09
    çķ¶åľ°
    -0.09
    æĢľ
    -0.09
    羣çļĦ
    -0.09
    POSITIVE LOGITS
     sẵn
    0.10
    tent
    0.09
    .PARAM
    0.08
    åĴĮæĬĢæľ¯
    0.08
    å®ĥåı¯ä»¥
    0.08
     оÑĦоÑĢм
    0.08
    åĴĮåľ°åĮº
    0.07
    eof
    0.07
    sters
    0.07
     nc
    0.07
    Activations Density 0.145%

    No Known Activations