© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29458
    Prev
    Next
    INDEX
    Explanations

    deficiency

    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
    Negative Logits
    åħļåĴĮ
    -0.09
    å½ĵä¹ĭ
    -0.09
    merc
    -0.09
    å¥łåŁº
    -0.09
    ä¸ĵç§ij
    -0.09
    纶
    -0.09
    Camb
    -0.08
    å¥ĸéĩij
    -0.08
    extracomment
    -0.08
    æ¡´
    -0.08
    POSITIVE LOGITS
    entes
    0.10
    ep
    0.10
    up
    0.08
    çļĦæĥħ
    0.08
     Reggie
    0.08
    NESS
    0.08
    oky
    0.08
    enta
    0.08
    illet
    0.08
    OrNil
    0.08
    Activations Density 0.743%

    No Known Activations