© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 3533
    Prev
    Next
    INDEX
    Explanations

    grades, GPA, standing

    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
    羣å¿ĥ
    -0.09
    ä¸ĢåĪ»
    -0.09
    ither
    -0.09
     thừa
    -0.09
    åIJĮèĥŀ
    -0.08
    åĪº
    -0.08
    ksi
    -0.08
    som
    -0.08
     Neo
    -0.08
    lef
    -0.08
    POSITIVE LOGITS
     педагог
    0.10
    olini
    0.10
    yper
    0.09
    æĭĪ
    0.09
    縱
    0.09
    phas
    0.09
    criptor
    0.09
    AdapterFactory
    0.08
    éĽ¹
    0.08
    yg
    0.08
    Activations Density 0.002%

    No Known Activations