© 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. 49255
    Prev
    Next
    INDEX
    Explanations

    left or right side

    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
    ono
    -0.11
    æīĭä¸Ń
    -0.09
    èĮĹ
    -0.08
     Arab
    -0.08
    è´µ
    -0.08
    icro
    -0.08
    æīĭéĩĮ
    -0.08
    éĻĦ件
    -0.08
    两åIJį
    -0.08
    两侧
    -0.08
    POSITIVE LOGITS
    纾
    0.10
    iy
    0.10
    .bz
    0.09
    ãĤµãĥĿãĥ¼ãĥĪ
    0.09
    eka
    0.09
    责任人
    0.09
    chooser
    0.09
    .Protocol
    0.09
    LETTE
    0.09
    éĤ£åıª
    0.09
    Activations Density 0.314%

    No Known Activations