© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61655
    Prev
    Next
    INDEX
    Explanations

    higher levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭĽ
    -0.09
    ady
    -0.08
    æī
    -0.08
    tings
    -0.07
    ä¸įè°ĥ
    -0.07
    ä¸ĵåĪ©çĶ³è¯·
    -0.07
     Bref
    -0.07
    _BODY
    -0.07
    ç«ĭæ¡Ī
    -0.07
    æ´ŀ
    -0.07
    POSITIVE LOGITS
     average
    0.08
    å¹³åĿĩæ°´å¹³
    0.08
    average
    0.08
    å¹³åĿĩ
    0.07
     Efficiency
    0.07
    EFF
    0.07
     efficiency
    0.07
    à¹Ģà¸īลีà¹Īย
    0.07
     efficiencies
    0.07
    bab
    0.07
    Activations Density 0.001%

    No Known Activations