© 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. 22446
    Prev
    Next
    INDEX
    Explanations

    costs and expenses

    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
     Ñĥдоб
    -0.10
     falls
    -0.09
    èĸ¤
    -0.09
     sold
    -0.09
    aka
    -0.08
    credit
    -0.08
     Falls
    -0.08
    èĭĴ
    -0.08
    æĸ¹ä¾¿
    -0.08
    à¹Ģส
    -0.08
    POSITIVE LOGITS
    ä¸į说
    0.13
    åĪĨ彩
    0.11
    éĹ»
    0.10
    è¿Ļç¬Ķ
    0.10
    ä¸Ģç¬Ķ
    0.10
    èģĺ请
    0.10
    é«ĺæĺĤ
    0.10
     Costs
    0.10
     Farrell
    0.09
    估计
    0.09
    Activations Density 0.057%

    No Known Activations