© 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. 48015
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    管å§Ķä¼ļ
    -0.13
    IMUM
    -0.10
    AndUpdate
    -0.09
    matic
    -0.09
    able
    -0.09
    å½¼æѤ
    -0.09
    UMENT
    -0.09
    uture
    -0.09
    zar
    -0.08
    å¾Ĺä½ı
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.11
    ness
    0.10
    UnderTest
    0.10
    enne
    0.10
    гад
    0.10
    ÑĢем
    0.10
    /Framework
    0.10
    mass
    0.09
    ialog
    0.09
    į
    0.09
    Activations Density 0.057%

    No Known Activations