© 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. 50133
    Prev
    Next
    INDEX
    Explanations

    short answer yes or no

    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
    ç»ĵåIJĪ
    -0.09
    åĸĦ
    -0.09
    æł¸å®ļ
    -0.09
    åįĬ天
    -0.09
    imony
    -0.09
     about
    -0.08
    ä»ĬçĶŁ
    -0.08
    ãģ¤ãĤĤãĤĬ
    -0.08
    人人
    -0.08
    èĽ°
    -0.08
    POSITIVE LOGITS
    ç´łè´¨æķĻèĤ²
    0.10
    稳åģ¥
    0.10
    åħ¶ä»ĸ人
    0.10
    åĪĨæµģ
    0.10
    PropertyParams
    0.09
     Utf
    0.09
    ä¼ĺ
    0.09
     опÑĭÑĤ
    0.09
    HeaderCode
    0.09
    çĥŃ度
    0.09
    Activations Density 0.006%

    No Known Activations