© 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. 20452
    Prev
    Next
    INDEX
    Explanations

    `AF`, `require`, `./`, `DisplayName`

    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
    士
    -0.07
    oyo
    -0.07
     oversight
    -0.07
     CIC
    -0.07
     Abed
    -0.07
    jab
    -0.06
    èľĴ
    -0.06
    ",-
    -0.06
    åĩºéĶħ
    -0.06
     turb
    -0.06
    POSITIVE LOGITS
    符
    0.07
    åĩ«
    0.07
     нав
    0.07
    æ´
    0.07
    orter
    0.07
    edel
    0.07
    åIJĮä¸Ģ
    0.07
    صÙĦ
    0.07
    aname
    0.07
    serial
    0.06
    Activations Density 0.065%

    No Known Activations