© 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. 57178
    Prev
    Next
    INDEX
    Explanations

    information retrieval corpus

    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
    å®ĺæĸ¹å¾®ä¿¡
    -0.11
    igner
    -0.10
     Moms
    -0.09
    æĺı
    -0.09
    å¼
    -0.09
    æİĸ
    -0.09
    _CT
    -0.09
    Translator
    -0.09
    åĵ²
    -0.09
    imat
    -0.09
    POSITIVE LOGITS
    _corpus
    0.09
    ä¸įä¼ļåĨį
    0.09
     corpor
    0.09
    (Text
    0.09
    anted
    0.09
    ucene
    0.09
    ç¿ĺ
    0.08
    yu
    0.08
    çİĩè¾¾åĪ°
    0.08
     Corpus
    0.08
    Activations Density 0.168%

    No Known Activations