© 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. 9298
    Prev
    Next
    INDEX
    Explanations

    new followed by nouns

    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
    èĪ¬
    -0.09
    åĨı
    -0.08
     unload
    -0.08
    èı²
    -0.08
    xious
    -0.08
    ÑĤан
    -0.08
    éĶĢ
    -0.08
    .optimize
    -0.08
    ä¸ĵä¸ļæĬĢæľ¯
    -0.08
    ayed
    -0.08
    POSITIVE LOGITS
    åİŁåĪĽ
    0.10
    ä»Ļ女
    0.10
    åİŁæľīçļĦ
    0.09
    åĪĽå»ºå·¥ä½ľ
    0.09
    cratch
    0.09
    uess
    0.09
    ä»İ严
    0.09
    _instances
    0.09
    å§ĭç»ĪåĿļæĮģ
    0.09
     ÑģÑĤаÑĢ
    0.09
    Activations Density 0.082%

    No Known Activations