© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10070
    Prev
    Next
    INDEX
    Explanations

    exams and examinations

    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
    åīįçŀ»
    -0.11
    æĭĨ
    -0.10
    èĢĺ
    -0.10
    æģĥ
    -0.09
    aho
    -0.09
    _SETUP
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    èĥŀ
    -0.09
    éĩį度
    -0.09
    uet
    -0.08
    POSITIVE LOGITS
    èĢĥè¯ķ
    0.24
    èĢĥ試
    0.18
     exam
    0.17
     exams
    0.17
    èĢĥåľº
    0.16
    ä¸ŃèĢĥ
    0.14
    é«ĺèĢĥ
    0.14
    è¯ķåį·
    0.14
    ìĭľíĹĺ
    0.13
    èĢĥ
    0.13
    Activations Density 0.063%

    No Known Activations