© 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. 29889
    Prev
    Next
    INDEX
    Explanations

    numbers and variables in mathematical or code contexts

    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
    é¾ĻçļĦ
    -0.07
     '');
    -0.07
    iss
    -0.07
    atap
    -0.07
    ç³ł
    -0.06
    çĽ£
    -0.06
    åħ¶äºĮ
    -0.06
    hiba
    -0.06
    åŃIJä¸Ĭ
    -0.06
    è¿IJåĬ¨ä¸Ń
    -0.06
    POSITIVE LOGITS
    ç£
    0.08
    çĴĢ
    0.08
    ód
    0.07
    erede
    0.07
    aty
    0.07
     soud
    0.07
    æļ
    0.07
    (CC
    0.06
    éľľ
    0.06
    liers
    0.06
    Activations Density 0.040%

    No Known Activations