© 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. 20691
    Prev
    Next
    INDEX
    Explanations

    horizontal context

    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
    ered
    -0.08
    aker
    -0.08
    个éĹ®é¢ĺ
    -0.07
    fully
    -0.07
    รà¹īาย
    -0.07
    年头
    -0.07
    /remove
    -0.07
    fél
    -0.07
    oule
    -0.07
    个
    -0.06
    POSITIVE LOGITS
    ness
    0.13
    ities
    0.10
    ity
    0.09
    idades
    0.08
    -ish
    0.08
    _ctxt
    0.08
    ampton
    0.08
    ization
    0.08
    اض
    0.08
    isht
    0.08
    Activations Density 0.009%

    No Known Activations