© 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. 11066
    Prev
    Next
    INDEX
    Explanations

    numbers and characters

    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
    éĿĴå±±
    -0.06
    Õ¹
    -0.06
    åĪ¶
    -0.06
    åıij
    -0.06
    rum
    -0.06
    anean
    -0.06
    <
    -0.06
    ower
    -0.06
     asa
    -0.05
     UN
    -0.05
    POSITIVE LOGITS
    uskan
    0.08
    賦
    0.08
    imenti
    0.08
    akil
    0.08
    æĥŁä¸Ģ
    0.08
    ãĤ¯ãĥ¼ãĥ«
    0.07
    empor
    0.07
    åıªæľīä¸Ģ个
    0.07
    å¼Ģå±ķ好
    0.07
    çļĦåĶ¯ä¸Ģ
    0.07
    Activations Density 0.060%

    No Known Activations