© 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. 57747
    Prev
    Next
    INDEX
    Explanations

    describes or explains reality

    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
    æł¼å¤ĸ
    -0.07
    çļĦä¸ĢåĪĩéĥ½
    -0.06
    èĬ±èIJ½
    -0.06
    nt
    -0.06
    lah
    -0.06
    æłijä¸ĭ
    -0.06
     Fallon
    -0.06
    iers
    -0.06
    å®ĮåĸĦçļĦ
    -0.06
    èĬ±æŶéĹ´
    -0.06
    POSITIVE LOGITS
     intended
    0.10
    å®ŀéĻħæĥħåĨµ
    0.10
     reality
    0.09
    羣缸
    0.09
     true
    0.09
     accurately
    0.09
     ÑģÑĥÑĤÑĮ
    0.09
     realities
    0.09
    å®ŀéĻħ
    0.09
    å®ŀæĥħ
    0.08
    Activations Density 0.080%

    No Known Activations