© 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. 4505
    Prev
    Next
    INDEX
    Explanations

    high-level details

    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
    éģ¥
    -0.10
     manh
    -0.08
    èĩ§
    -0.08
    éģĹ
    -0.08
    æģ¼
    -0.08
    abwe
    -0.08
    .boot
    -0.08
    箧
    -0.08
    åIJĮè¡Į
    -0.08
    ÑĪив
    -0.08
    POSITIVE LOGITS
    å®ıè§Ĥ
    0.24
    æķ´ä½ĵ
    0.16
     macro
    0.16
    大å±Ģ
    0.15
    macro
    0.15
     Macro
    0.15
    å®ı
    0.14
    æĢ»ä½ĵ
    0.14
    åħ¨å±Ģ
    0.14
    大çļĦ
    0.13
    Activations Density 0.095%

    No Known Activations