© 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. 48036
    Prev
    Next
    INDEX
    Explanations

    launching sequences

    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
    mlink
    -0.10
    aceous
    -0.10
    Į
    -0.10
     Ñĩа
    -0.09
    ities
    -0.09
    çķĮçļĦ
    -0.09
    avig
    -0.09
    ä¸įä½ı
    -0.09
    leÅŁ
    -0.09
    èĨĤ
    -0.09
    POSITIVE LOGITS
    pad
    0.14
    baugh
    0.10
    able
    0.10
    ero
    0.10
    ned
    0.10
    äºĨ许å¤ļ
    0.09
    ermo
    0.09
    леÑĤ
    0.09
    izable
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    Activations Density 0.024%

    No Known Activations