© 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. 24846
    Prev
    Next
    INDEX
    Explanations

    defenders or receptors

    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
     central
    -0.08
     Gow
    -0.07
    uk
    -0.07
    epen
    -0.07
     uc
    -0.06
     Central
    -0.06
    æĬķ
    -0.06
    åŁİ
    -0.06
    åŁİåĨħ
    -0.06
    central
    -0.06
    POSITIVE LOGITS
    itemap
    0.08
    èļ¤
    0.08
    akis
    0.07
    teh
    0.07
    аÑĤов
    0.07
    neys
    0.07
    CHIP
    0.07
    zea
    0.07
    teri
    0.07
    为è¾ħ
    0.07
    Activations Density 0.161%

    No Known Activations