© 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. 64175
    Prev
    Next
    INDEX
    Explanations

    `.g`

    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
     wishing
    -0.07
    åĵĦ
    -0.07
    alist
    -0.07
    cala
    -0.07
    à¯įப
    -0.06
    ality
    -0.06
    bearing
    -0.06
    çĶ
    -0.06
    اس
    -0.06
    为é¦ĸ
    -0.06
    POSITIVE LOGITS
    åĭ¢
    0.08
    çļĦå°±æĺ¯
    0.07
    zyb
    0.07
    -indent
    0.07
    ueb
    0.07
    innen
    0.07
    UTT
    0.07
    ikt
    0.07
    igo
    0.07
    chu
    0.07
    Activations Density 0.001%

    No Known Activations