© 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. 22579
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code

    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
    /pp
    -0.07
    å¬
    -0.07
    bb
    -0.07
    ä¸įäºī
    -0.07
    asti
    -0.07
    buk
    -0.07
     Cip
    -0.07
    länd
    -0.06
    延éķ¿
    -0.06
    aland
    -0.06
    POSITIVE LOGITS
    ynet
    0.08
    isson
    0.08
    èļģ
    0.07
    éĤ£ä¹ĪçļĦ
    0.07
    ibs
    0.06
    ardini
    0.06
     probability
    0.06
    æ®ĭ
    0.06
    巾帼
    0.06
    ä¹ħä¹ħ
    0.06
    Activations Density 0.003%

    No Known Activations