© 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. 17670
    Prev
    Next
    INDEX
    Explanations

    college courses

    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
    èı½
    -0.10
    çĶĺ
    -0.09
    ç§Ĩ
    -0.09
    ç±´
    -0.09
     Kut
    -0.09
    æ¡ģ
    -0.08
    åıªæĥ³
    -0.08
    æľ½
    -0.08
    强èĢħ
    -0.08
    èĽ¹
    -0.08
    POSITIVE LOGITS
     courses
    0.14
     classes
    0.12
    课ç¨ĭ
    0.11
    classes
    0.11
     cursos
    0.11
     Courses
    0.11
    åĶĨ
    0.11
    Courses
    0.10
    å¼Ģ设
    0.10
    courses
    0.10
    Activations Density 0.082%

    No Known Activations