© 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. 58924
    Prev
    Next
    INDEX
    Explanations

    soybean and related products

    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
    æĪ¡
    -0.09
    çŃĸ
    -0.09
    icker
    -0.09
    èĻ¢
    -0.09
    åijĬ
    -0.09
    INNER
    -0.08
    MR
    -0.08
    ä¹ı
    -0.08
    çĶ³
    -0.08
    mse
    -0.08
    POSITIVE LOGITS
    è±ĨæµĨ
    0.11
    è±ģ
    0.10
    大è±Ĩ
    0.10
    _CONVERT
    0.10
    .anim
    0.09
    opr
    0.09
    éĽ¾
    0.09
    沤
    0.09
    沪
    0.09
    æµģ产
    0.09
    Activations Density 0.060%

    No Known Activations