© 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. 33542
    Prev
    Next
    INDEX
    Explanations

    Italian places and names

    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
    èĭķ
    -0.10
    æĭīæĸ¯
    -0.09
    ãģĹãģķ
    -0.09
     Saskatchewan
    -0.09
    æĪIJéĥ½
    -0.09
    涪
    -0.08
    æľīæķĪ
    -0.08
    tright
    -0.08
    çļĭ
    -0.08
     repro
    -0.08
    POSITIVE LOGITS
    æ²Ĥ
    0.09
     Greek
    0.09
    é½IJé²ģ
    0.09
    çĶµæ°Ķ
    0.09
    å¸ĮèħĬ
    0.08
     Napoli
    0.08
    éĤ¾
    0.08
    家åĸ»æĪ·æĻĵ
    0.08
     alternating
    0.08
    Pes
    0.08
    Activations Density 0.034%

    No Known Activations