© 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. 40238
    Prev
    Next
    INDEX
    Explanations

    quad

    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¸Ģæ°Ķ
    -0.07
     frattempo
    -0.07
     ints
    -0.06
    ä½ĨçĶ±äºİ
    -0.06
    oret
    -0.06
    ä¾ĭå¦Ĥ
    -0.06
    à¸Ńà¸Ķี
    -0.06
    æī¶
    -0.06
     however
    -0.06
    uton
    -0.06
    POSITIVE LOGITS
    話ãģĮ
    0.08
    าà¸ĩ
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    иÑģÑĤи
    0.08
    家å®Ŀ
    0.07
    häuser
    0.07
    家æĺ¯
    0.07
    psc
    0.07
    ppe
    0.07
    á»įt
    0.07
    Activations Density 0.005%

    No Known Activations