© 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. 38932
    Prev
    Next
    INDEX
    Explanations

    Chelsea, Bastille, David, stable

    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
    inja
    -0.07
    think
    -0.07
    agé
    -0.07
    èĢĮåĸ»
    -0.07
    truct
    -0.07
    emies
    -0.07
    оÑĤоÑĢ
    -0.07
    atina
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
    ollow
    -0.07
    POSITIVE LOGITS
    æ°ı
    0.09
    ä¹ĭæģĭ
    0.08
    ites
    0.07
    åıijæĮ¥å¥½
    0.07
    æĹłæģĻ
    0.07
    大å®Ŀ
    0.07
    opot
    0.07
    ä¹ĭéŃĤ
    0.07
    åĪĿè¯ķ
    0.06
    ensis
    0.06
    Activations Density 0.017%

    No Known Activations