© 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. 35466
    Prev
    Next
    INDEX
    Explanations

    non-English characters / foreign text

    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
    å¤ļ项
    -0.09
     stereotype
    -0.09
    ä¹Łä¸įæķ¢
    -0.08
    å±ĢéĿ¢
    -0.08
    åħ¸åŀĭ
    -0.08
    çģ«çĥ§
    -0.08
    routine
    -0.08
    éĥ½ä¸įæķ¢
    -0.08
    ValuePair
    -0.08
    è¯Ħå§Ķ
    -0.08
    POSITIVE LOGITS
    lage
    0.10
    æĴ©
    0.10
    .lift
    0.09
    å·Ŀ
    0.09
    /repos
    0.09
    èIJ½
    0.09
    å®ŀåľ¨
    0.09
    à¸Ļาม
    0.09
    æĪ´ä¸Ĭ
    0.09
    verb
    0.08
    Activations Density 0.099%

    No Known Activations