© 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. 38058
    Prev
    Next
    INDEX
    Explanations

    bug reports or descriptions

    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
    паÑĢ
    -0.08
    åĬŁè¯¾
    -0.08
    鼷æĸ¯
    -0.08
     Shades
    -0.08
    ibbon
    -0.08
    .isSuccess
    -0.08
    è§Ħéģ¿
    -0.08
    OM
    -0.08
    ãĥ¼ãĤ·
    -0.08
    à¸ļรร
    -0.07
    POSITIVE LOGITS
    åºĵéĩĮ
    0.10
    angu
    0.09
    缸åħ³éĥ¨éŨ
    0.09
    åĨ¶çĤ¼
    0.09
    åĴĦ
    0.09
    亲èĩª
    0.09
    éĻ¡
    0.09
    嵯
    0.09
    roma
    0.08
    Tickets
    0.08
    Activations Density 0.231%

    No Known Activations