© 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. 5900
    Prev
    Next
    INDEX
    Explanations

    websites and programming contexts

    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
     Furn
    -0.09
    çĽij管éĥ¨éŨ
    -0.08
    æģŃæķ¬
    -0.08
    èī®
    -0.08
    ä½ľä¸ļ
    -0.08
    æķ¬
    -0.08
    履约
    -0.08
    ç¹ģ
    -0.08
    以éĺ²
    -0.08
    ç½ijéĢļ
    -0.08
    POSITIVE LOGITS
    æ¼
    0.09
    cul
    0.09
    éĻ¢éĻ¢éķ¿
    0.09
    .scalajs
    0.08
    çĸij
    0.08
    éĻ¢åī¯éĻ¢éķ¿
    0.08
    PMC
    0.08
    SQL
    0.08
    奥
    0.08
    èĶ¬
    0.08
    Activations Density 0.356%

    No Known Activations