© 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. 11672
    Prev
    Next
    INDEX
    Explanations

    assessment, evaluation, exam

    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
    ç°§
    -0.09
    ä¸ĢçĤ¹
    -0.09
    Prototype
    -0.09
     Lah
    -0.08
    æĪ¢
    -0.08
     haz
    -0.08
     puss
    -0.08
     hed
    -0.08
    eras
    -0.08
    nip
    -0.08
    POSITIVE LOGITS
    è¯Ħä¼°
    0.14
    审è§Ĩ
    0.13
    åĪĨæŀIJ
    0.12
    çİ°çĬ¶
    0.11
    gratis
    0.11
    çľĭäºĨä¸Ģ
    0.10
    è¯ĬæĸŃ
    0.10
    çĶĦ
    0.10
     assessment
    0.09
    perc
    0.09
    Activations Density 0.089%

    No Known Activations