© 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. 26118
    Prev
    Next
    INDEX
    Explanations

    sugar

    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
    sing
    -0.08
    вок
    -0.08
    iqu
    -0.07
    ailer
    -0.07
    éľĨ
    -0.07
    anden
    -0.07
    èĮĥæĸĩç½ij
    -0.07
    spf
    -0.07
    ÑīеÑĤ
    -0.07
    деÑĨ
    -0.07
    POSITIVE LOGITS
    èĶĹç³ĸ
    0.09
     syrup
    0.09
    ç³ĸ
    0.08
    èij¡èIJĦç³ĸ
    0.08
    çĶľèľľ
    0.08
     ÑģаÑħаÑĢ
    0.08
     sugar
    0.08
     glucose
    0.08
     mell
    0.08
    åij³çļĦ
    0.08
    Activations Density 0.027%

    No Known Activations