© 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. 62167
    Prev
    Next
    INDEX
    Explanations

    universities and cities

    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
    éĻįä½İæĪIJæľ¬
    -0.10
    bour
    -0.09
    Reuse
    -0.09
    -toggler
    -0.08
    éªij士
    -0.08
    æ¦ľ
    -0.08
    åĿª
    -0.08
    éĨī
    -0.08
     astore
    -0.08
     nou
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
    ниÑĨа
    0.09
     wÅĤ
    0.08
    åıĮæīĭ
    0.08
    游æĪıéĩĮçļĦ
    0.08
     Martha
    0.08
    æ¼ī
    0.08
    çµIJ
    0.08
    atti
    0.08
    lip
    0.08
    Activations Density 0.002%

    No Known Activations