© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2397
    Prev
    Next
    INDEX
    Explanations

    cliff","fiscal cliff"",""orphan works"",""grandfather rights"",""man cave"

    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
    iphy
    -0.07
     Grosso
    -0.07
     hoÃłng
    -0.07
    ONS
    -0.06
    rops
    -0.06
    æ¸ĬæºIJ
    -0.06
    arre
    -0.06
    ëį°
    -0.06
    æľīå¿ĥ
    -0.06
    èĶĶ
    -0.06
    POSITIVE LOGITS
    ä¹ĭ称çļĦ
    0.14
    èĪ¬çļĦ
    0.12
    èĪ¬åľ°
    0.10
    ä¸Ģæł·çļĦ
    0.10
    èĪ¬
    0.09
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.09
    æł·çļĦ
    0.09
    åĦ¿çļĦ
    0.09
    -like
    0.09
    å¼ıçļĦ
    0.09
    Activations Density 0.309%

    No Known Activations