© 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. 65212
    Prev
    Next
    INDEX
    Explanations

    will / may followed by verb or only

    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
    ä¸įåİ»
    -0.08
    explicit
    -0.08
    ä¸įèµ°
    -0.07
    åİ»äºĨ
    -0.07
    ---</
    -0.07
    ç¦ıåĪ©
    -0.07
    ç»ıå¾Ĺèµ·
    -0.07
    à¤ļ
    -0.07
    ussen
    -0.07
    umer
    -0.07
    POSITIVE LOGITS
    ibre
    0.07
    dea
    0.07
    iber
    0.06
    olos
    0.06
    ebro
    0.06
    èĢģçĪ¹
    0.06
    ulkan
    0.06
    lise
    0.06
    ospace
    0.06
    åIJĭ
    0.06
    Activations Density 0.001%

    No Known Activations