© 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. 1132
    Prev
    Next
    INDEX
    Explanations

    craft and art supplies

    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
    æŁ¥éªĮ
    -0.10
    çĬ¯
    -0.09
    ç½ħ
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    寮
    -0.09
    StateException
    -0.08
    мÑĭÑĪ
    -0.08
    çĻ½é©¬
    -0.08
    ÙĬØ«
    -0.08
    basePath
    -0.08
    POSITIVE LOGITS
    uno
    0.10
    eker
    0.10
    社
    0.09
    rama
    0.09
    çķĮ
    0.09
    æijĬ
    0.09
    enco
    0.08
    æ¼Ĩ
    0.08
    麻
    0.08
    etten
    0.08
    Activations Density 0.006%

    No Known Activations