© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61549
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code

    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
    prising
    -0.07
    ssel
    -0.07
    èĽŁ
    -0.07
    è¾£
    -0.07
    麻çĹ¹
    -0.07
     Sommer
    -0.07
    alogy
    -0.07
    ãģĦãģı
    -0.06
    UG
    -0.06
    ube
    -0.06
    POSITIVE LOGITS
    astas
    0.08
    ä¸įçķĻ
    0.08
    çĮ¬
    0.08
    éĢļ
    0.08
    -cancel
    0.08
    æ²»
    0.07
    شتÙĩ
    0.07
     Rear
    0.07
    adir
    0.07
    建åĨĽ
    0.07
    Activations Density 0.012%

    No Known Activations