© 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. 19044
    Prev
    Next
    INDEX
    Explanations

    groups and moieties

    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
    ä¹ĭå¢ĥ
    -0.07
    <|box_end|>
    -0.07
    alb
    -0.07
    ly
    -0.07
    å±ħæĺĵ
    -0.07
    imizer
    -0.07
    हà¥Ģà¤Ĥ
    -0.07
    بØŃ
    -0.07
    ién
    -0.06
    -ish
    -0.06
    POSITIVE LOGITS
    /method
    0.08
    umin
    0.08
    uards
    0.08
    /module
    0.07
    ært
    0.07
    edin
    0.07
    iedad
    0.07
    wechs
    0.07
    ALLERY
    0.07
    æĹģçļĦ
    0.07
    Activations Density 0.013%

    No Known Activations