© 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. 39037
    Prev
    Next
    INDEX
    Explanations

    decades

    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
    er
    -0.12
    ty
    -0.11
    _supported
    -0.10
    çIJĨä¼ļ
    -0.10
    zelf
    -0.10
    isoft
    -0.10
    ä¸ĭ次
    -0.10
    æĻ°
    -0.09
    å½ĵ代
    -0.09
    ties
    -0.09
    POSITIVE LOGITS
    -era
    0.11
    -old
    0.09
    ä¸ŃæľŁ
    0.09
    éĢ¡
    0.08
    æĿ¥ä¸´
    0.08
    à¹Ģศ
    0.08
    -most
    0.08
     назад
    0.08
    /month
    0.07
    /post
    0.07
    Activations Density 0.021%

    No Known Activations