© 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. 24265
    Prev
    Next
    INDEX
    Explanations

    rendered or showed

    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
     banner
    -0.09
    ote
    -0.08
    ourd
    -0.08
    CUR
    -0.08
    好å¥ĩ
    -0.08
    çı°
    -0.08
    erd
    -0.08
     cursor
    -0.08
     transform
    -0.08
    åģļçļĦäºĭ
    -0.08
    POSITIVE LOGITS
    éĽĮ
    0.10
    åIJģ
    0.10
    UED
    0.09
    annis
    0.09
    ðŁĶ¶
    0.09
    èµ·æĿ¥
    0.09
    OTOS
    0.09
    ä¸īçŃīå¥ĸ
    0.09
    è··
    0.09
    ÑĤÑĮÑģÑı
    0.09
    Activations Density 0.233%

    No Known Activations