© 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. 760
    Prev
    Next
    INDEX
    Explanations

    cisap, bovis, occupant, radon

    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
    èĻı
    -0.10
    çºł
    -0.09
    gMaps
    -0.09
    çŃīé¢ĨåŁŁ
    -0.08
    ıt
    -0.08
    edException
    -0.08
    çłº
    -0.08
    åģļ大
    -0.08
    ItemImage
    -0.08
    å¼
    -0.08
    POSITIVE LOGITS
    主è¦ģéĽĨä¸Ń
    0.09
    主è¦ģ
    0.09
    åħ·ä½ĵ
    0.09
     Fantasy
    0.08
     perse
    0.08
    åĪĨ为
    0.08
    羣è¯ļ
    0.08
    羡æħķ
    0.08
    éĽĨä¸Ńåľ¨
    0.08
    imeo
    0.08
    Activations Density 0.811%

    No Known Activations