© 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. 55787
    Prev
    Next
    INDEX
    Explanations

    gold, fast

    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
    åŀ¸
    -0.09
    á»ijc
    -0.09
    rit
    -0.08
     conj
    -0.08
    æĸ¯åŁº
    -0.08
    åijµæĬ¤
    -0.08
     Atari
    -0.08
     dá»ĭ
    -0.08
    åĿIJçĿĢ
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    åĴĮ个人
    0.10
    ä¸Ģè§Ĵ
    0.10
    åħ¬å¸ĥçļĦ
    0.09
    ÅĤam
    0.09
    å¼Ĥåľ°
    0.09
    åĪ·
    0.09
    é³Ł
    0.09
    .TEXTURE
    0.09
    ä¼ijåģĩ
    0.09
    ç¿ħèĨĢ
    0.09
    Activations Density 0.123%

    No Known Activations