© 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. 13115
    Prev
    Next
    INDEX
    Explanations

    relative descriptions

    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
    éĿ©åij½åħĪçĥĪ
    -0.08
    داÙĨ
    -0.07
    oller
    -0.07
     оÑģмо
    -0.07
    aits
    -0.07
    ÙĪÙĤØ©
    -0.07
    çľĭåĪ°çļĦ
    -0.07
    заÑħ
    -0.07
    ertest
    -0.06
    aw
    -0.06
    POSITIVE LOGITS
    ÛĮد
    0.07
    OCO
    0.07
    loh
    0.07
    esti
    0.07
    èĤºèħij
    0.07
    templates
    0.06
    osi
    0.06
    IDE
    0.06
    _py
    0.06
    sns
    0.06
    Activations Density 1.434%

    No Known Activations