© 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. 61279
    Prev
    Next
    INDEX
    Explanations

    follow

    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
    åŃĶéĽĢ
    -0.10
    enburg
    -0.10
    otify
    -0.10
    /gui
    -0.10
    olver
    -0.10
    idata
    -0.09
    NEL
    -0.09
    Ĭ
    -0.09
    æĭ±
    -0.09
    .MEDIA
    -0.09
    POSITIVE LOGITS
    ings
    0.09
    责任
    0.09
    å·¥ç¨ĭ建设
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    æĽ·
    0.09
    æ§ģ
    0.08
    ingly
    0.08
    ÑģÑı
    0.08
    imiento
    0.08
    æĿijéķĩ
    0.08
    Activations Density 0.020%

    No Known Activations