© 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. 3950
    Prev
    Next
    INDEX
    Explanations

    so all, so you, so I, so now

    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
     Fakt
    -0.07
    åĴĮå¿«ä¹IJ
    -0.07
    imoni
    -0.06
    òng
    -0.06
    èĬ¬
    -0.06
    amento
    -0.06
    loge
    -0.06
     паÑģÑģ
    -0.06
    unen
    -0.06
    æ±¾
    -0.06
    POSITIVE LOGITS
    inverse
    0.08
    并åıĸå¾Ĺ
    0.07
    kut
    0.07
     inverse
    0.07
    ovil
    0.07
     expectedResult
    0.07
    گر
    0.07
    ambre
    0.07
    |array
    0.07
    ä¸ĢåľĪ
    0.07
    Activations Density 0.005%

    No Known Activations