© 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. 36328
    Prev
    Next
    INDEX
    Explanations

    calotte

    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
    emi
    -0.09
    åĴĮ社ä¼ļ
    -0.08
    çħ½
    -0.08
    emic
    -0.07
    æĸ°ä¸ĸ纪
    -0.07
    soc
    -0.07
    éģı
    -0.07
    åģ·
    -0.07
    åĮĹ京åĨ¬å¥¥
    -0.07
    Encoding
    -0.07
    POSITIVE LOGITS
    akedown
    0.10
    èĮ¶
    0.10
    _verbose
    0.10
    IRR
    0.09
    _misc
    0.09
    uib
    0.09
     marshaller
    0.09
    osex
    0.09
    ALIGN
    0.09
    滹
    0.09
    Activations Density 0.143%

    No Known Activations