© 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. 49031
    Prev
    Next
    INDEX
    Explanations

    was followed by past actions or legal events

    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
    osl
    -0.10
    unes
    -0.09
    ãĤ²
    -0.09
    æĦŁè§īèĩªå·±
    -0.08
    icing
    -0.08
    ace
    -0.08
    éĤª
    -0.08
    è¿ĻäºĽäºº
    -0.08
    éŨæĪ·
    -0.08
    äºĭåĦ¿
    -0.08
    POSITIVE LOGITS
    éĦ¯
    0.09
    èĩ¼
    0.09
    4
    0.08
    8
    0.08
    çĴ¨
    0.08
    ç»Ģ
    0.08
    5
    0.08
    èªĵè¨Ģ
    0.08
    enis
    0.08
    3
    0.08
    Activations Density 0.044%

    No Known Activations