© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52368
    Prev
    Next
    INDEX
    Explanations

    Silverlight or Abercrombie

    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
    полнен
    -0.10
    avis
    -0.10
    ائد
    -0.09
    linky
    -0.09
    å¿įä¸įä½ı
    -0.09
    éĹľæĸ¼
    -0.09
    èĩªå¸¦
    -0.09
    SWG
    -0.09
    ows
    -0.09
    ʾ
    -0.09
    POSITIVE LOGITS
    lette
    0.09
    put
    0.08
     patri
    0.08
    oral
    0.08
    èĪĶ
    0.08
     Flip
    0.08
    åľ°ä¸Ĭ
    0.08
    most
    0.08
    对ç«ĭ
    0.08
    ãģĿãģĨãģł
    0.07
    Activations Density 0.006%

    No Known Activations