© 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. 10602
    Prev
    Next
    INDEX
    Explanations

    news agencies and wires

    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
     Instances
    -0.09
     addict
    -0.09
    æİĴæ°Ķ
    -0.08
    UMP
    -0.08
    令
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    _profiles
    -0.08
    town
    -0.08
     captain
    -0.08
    InstanceId
    -0.08
    POSITIVE LOGITS
    è·¨è¶Ĭ
    0.10
    Reuters
    0.10
    æĸ°åįİ
    0.10
    æĸ°åįİ社
    0.09
     stocks
    0.09
     Reuters
    0.09
    éŀŃ
    0.09
     news
    0.09
    \API
    0.09
     News
    0.09
    Activations Density 0.114%

    No Known Activations