© 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. 33795
    Prev
    Next
    INDEX
    Explanations

    Mozilla Foundation

    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
    éĺĻ
    -0.07
    olesc
    -0.07
     Monten
    -0.07
     ky
    -0.07
     Appalach
    -0.06
    æĹłåıį
    -0.06
    .asc
    -0.06
    ips
    -0.06
     heir
    -0.06
    agos
    -0.06
    POSITIVE LOGITS
     dini
    0.07
    ç¡ķ
    0.07
    çĩİ
    0.07
    abat
    0.07
    ç«ĭåį³è´Ńä¹°
    0.07
    _unpack
    0.07
    èķĥ
    0.07
    egger
    0.06
    ä¿ĿåĪ©
    0.06
    å¸Ĥ
    0.06
    Activations Density 0.003%

    No Known Activations