© 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. 51032
    Prev
    Next
    INDEX
    Explanations

    login prompt, query, database, site

    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
    upro
    -0.07
    /releases
    -0.07
    说ä¸į
    -0.07
     أد
    -0.06
     splet
    -0.06
    å¦Ĥæŀľè¯´
    -0.06
     Patton
    -0.06
    aranja
    -0.06
    @email
    -0.06
    为ä¿Ŀè¯ģ
    -0.06
    POSITIVE LOGITS
     =
    0.08
    :&
    0.08
    rus
    0.08
    :
    0.08
    è¡ħ
    0.08
     âĨĴ
    0.07
    çĿĢæĪij们çļĦ
    0.07
     ->
    0.07
    +:
    0.07
     vs
    0.07
    Activations Density 0.081%

    No Known Activations