© 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. 56952
    Prev
    Next
    INDEX
    Explanations

    ancients' names

    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
    çģ«çĥ§
    -0.09
    éĢĦ
    -0.09
    amat
    -0.09
    èIJ½åľ¨
    -0.08
     embarrass
    -0.08
    å¾Ĥ
    -0.08
    éĢ¼è¿ij
    -0.08
    adol
    -0.08
     iT
    -0.08
    èIJ½
    -0.08
    POSITIVE LOGITS
    绣çŃ¹æİ¨è¿Ľ
    0.09
     ÑģпеÑĨиалÑĮно
    0.09
    éĨĴäºĨ
    0.08
    ä½ľåĵģåĨħ容
    0.08
    æĪĹ
    0.08
    éij«
    0.08
    æīĵåĩ»
    0.08
     Remaining
    0.07
     Finished
    0.07
     Spare
    0.07
    Activations Density 0.247%

    No Known Activations