© 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. 39317
    Prev
    Next
    INDEX
    Explanations

    award ceremony

    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
    imation
    -0.11
    ï¸ı
    -0.10
    OrCreate
    -0.10
    ument
    -0.09
    folk
    -0.09
    paces
    -0.09
    heel
    -0.09
    à¸ģระà¸Ĺ
    -0.09
    innen
    -0.09
    iness
    -0.09
    POSITIVE LOGITS
    ally
    0.11
    sek
    0.09
    çĺķ
    0.09
    asters
    0.09
     Bran
    0.09
    åľ°çĤ¹
    0.09
    çļ¿
    0.09
    à¸ĵ
    0.09
     TForm
    0.09
    ously
    0.08
    Activations Density 0.006%

    No Known Activations