© 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. 58182
    Prev
    Next
    INDEX
    Explanations

    social media and apps

    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
    ä¸įç¦ģ
    -0.09
    éĤ¯
    -0.09
    çľĭä¸įåĩº
    -0.08
    editable
    -0.08
    å²ļ
    -0.08
    geh
    -0.08
    åĬŁ
    -0.08
    åĽ½åºĨ
    -0.08
    åıªåī©
    -0.08
    ermann
    -0.08
    POSITIVE LOGITS
    åĽłä¸ºæĪij
    0.09
    utor
    0.08
    affe
    0.08
    urtle
    0.08
    éĿ¢çĽ®
    0.08
    plat
    0.08
    éĨª
    0.08
    .pat
    0.08
    annel
    0.08
    å°ıä¼Ļä¼´
    0.08
    Activations Density 0.036%

    No Known Activations