© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19267
    Prev
    Next
    INDEX
    Explanations

    solar cells / photovoltaics

    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
    ç¼Ŀ
    -0.09
    illon
    -0.09
    ä»İ严
    -0.08
    _SCL
    -0.08
    èĽĭçĻ½è´¨
    -0.08
    对çħ§æ£ĢæŁ¥
    -0.08
    æĶĴ
    -0.08
    æĻ®æ³ķ
    -0.08
    agan
    -0.08
    sa
    -0.08
    POSITIVE LOGITS
     ÑĤоÑĢ
    0.10
    åĩĨ
    0.09
    å®Ĺ
    0.09
    ç»Łè®¡æķ°æį®
    0.09
    istrict
    0.09
    ancell
    0.09
    æ·±åĬłå·¥
    0.09
    &view
    0.09
    abinet
    0.09
    端æŃ£
    0.09
    Activations Density 0.200%

    No Known Activations