© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8550
    Prev
    Next
    INDEX
    Explanations

    ASP.NET web controls

    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
    ifar
    -0.09
    ä¸įç¦ģ
    -0.09
    è´¬
    -0.09
    å¾ĢæĿ¥
    -0.09
    phet
    -0.09
    ×Ļ×ķ×Ŀ
    -0.09
    _loading
    -0.09
    chure
    -0.09
    èĮģ
    -0.09
    getExtension
    -0.09
    POSITIVE LOGITS
    çĤ¬
    0.09
    è¿ĻæĿ¡
    0.09
    1
    0.08
    çµ®
    0.08
    èIJ½
    0.08
    clubs
    0.08
    2
    0.08
    ãģ»ãģ©
    0.08
     Walton
    0.08
    0
    0.08
    Activations Density 0.408%

    No Known Activations