© 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. 30826
    Prev
    Next
    INDEX
    Explanations

    please followed by action

    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
    ä¹İ
    -0.08
    æĺĿ
    -0.08
     AUTHORS
    -0.08
     Ramp
    -0.08
    loh
    -0.08
    ivial
    -0.08
    _PLAN
    -0.08
    æĮĸæİĺ
    -0.08
    ä¸įä»ħè¦ģ
    -0.08
    Compatible
    -0.08
    POSITIVE LOGITS
    éĨį
    0.11
    诺
    0.10
    åıĸæļĸ
    0.09
    ç½ijåĿĢ
    0.08
    马æĭī
    0.08
    èĦ±
    0.08
    å±ŀ
    0.08
    缨
    0.08
    两边
    0.08
    åįİåĮĹ
    0.08
    Activations Density 0.038%

    No Known Activations