© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 51456
    Prev
    Next
    INDEX
    Explanations

    code syntax and method calls

    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
    .toCharArray
    -0.07
    gor
    -0.07
    ÙİØ±Ùİ
    -0.07
    èĬ¹
    -0.07
    çĹ´
    -0.06
    lach
    -0.06
    ç»İ
    -0.06
    ebre
    -0.06
     "|"
    -0.06
    ucks
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.08
    PageIndex
    0.07
    onge
    0.07
    Matcher
    0.07
    åģļäºĽ
    0.07
    veh
    0.07
    _CLEAN
    0.07
    èİ«éĿŀ
    0.07
    vect
    0.07
    omen
    0.07
    Activations Density 0.038%

    No Known Activations