© 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. 18107
    Prev
    Next
    INDEX
    Explanations

    Stein, Bernstein, Steinbeck

    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
    ities
    -0.11
    oral
    -0.10
    åŃIJéĩĮ
    -0.10
     dÃłng
    -0.10
    éĽªå±±
    -0.09
    Ĺ
    -0.09
    hone
    -0.09
    ired
    -0.09
    iance
    -0.08
    è§Ħç«ł
    -0.08
    POSITIVE LOGITS
    hardt
    0.12
    é¢ı
    0.10
    ãģĹãģ¾ãģĦ
    0.09
    ç
    0.09
    ovsky
    0.09
    baum
    0.09
    wards
    0.09
    ering
    0.09
    INGER
    0.08
    è·¯ä¸Ĭ
    0.08
    Activations Density 0.012%

    No Known Activations