© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52710
    Prev
    Next
    INDEX
    Explanations

    location and position

    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
    izoph
    -0.10
    å±Ī
    -0.10
    ptest
    -0.10
    ä¸įåIJĪ
    -0.10
    åIJĮç±»
    -0.09
    _pdata
    -0.09
    污
    -0.09
    æĪIJé¾Ļ
    -0.09
    repid
    -0.09
    ìºĺ
    -0.09
    POSITIVE LOGITS
    çļĦä½įç½®
    0.13
    ä½įç½®
    0.12
     location
    0.12
     coordinates
    0.10
    lies
    0.10
    çļĦåħ·ä½ĵ
    0.09
    mgr
    0.09
    location
    0.09
    ä½įäºİ
    0.09
    5
    0.09
    Activations Density 0.134%

    No Known Activations