© 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. 12848
    Prev
    Next
    INDEX
    Explanations

    mathematical function definitions

    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
    çħ§
    -0.07
    abda
    -0.07
    èĹīæѤ
    -0.07
    é¼ł
    -0.07
    å¿ħ究
    -0.07
    æĪŁ
    -0.06
     gu
    -0.06
    æĬĹ
    -0.06
    å°±æĺ¯äºĨ
    -0.06
    .Expr
    -0.06
    POSITIVE LOGITS
    bote
    0.07
    -bot
    0.07
    ("***
    0.07
    æ¾ľ
    0.06
    _inline
    0.06
     abat
    0.06
    alak
    0.06
    æ¹ĥ
    0.06
    ISR
    0.06
    bots
    0.06
    Activations Density 0.169%

    No Known Activations