© 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. 56111
    Prev
    Next
    INDEX
    Explanations

    Manufacturer, Home, south, www, bron, easy, last

    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
    reon
    -0.07
    emd
    -0.07
    positor
    -0.07
    idou
    -0.07
    batim
    -0.07
     diar
    -0.07
    adia
    -0.06
    мино
    -0.06
    rafo
    -0.06
    LETE
    -0.06
    POSITIVE LOGITS
    ict
    0.07
    ories
    0.07
    ille
    0.07
     itself
    0.07
    lek
    0.06
    cmc
    0.06
    antu
    0.06
    æ²¾
    0.06
     herself
    0.06
    cier
    0.06
    Activations Density 0.856%

    No Known Activations