© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    date format or calendar terms

    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»°
    -0.10
    çļĦ身份
    -0.10
    çļĦæ¯ĶèµĽ
    -0.09
    è´´
    -0.09
    \Annotation
    -0.09
    èĽĭ
    -0.09
    黾
    -0.09
     Taj
    -0.09
    辩
    -0.09
    çļĦæ¯Ķä¾ĭ
    -0.08
    POSITIVE LOGITS
    .ud
    0.08
    éĿĴå¹´
    0.08
    éľĩ
    0.07
    erd
    0.07
    ÃŃv
    0.07
    äºİæѤ
    0.07
    zem
    0.07
    Ãłng
    0.07
    nation
    0.07
    顶
    0.07
    Activations Density 0.242%

    No Known Activations