© 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. 42159
    Prev
    Next
    INDEX
    Explanations

    returns value

    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
    è¹Ł
    -0.07
    ıģ
    -0.07
    rase
    -0.07
     Trab
    -0.07
    /object
    -0.07
    idge
    -0.07
    è·
    -0.07
    ég
    -0.06
    heen
    -0.06
    çľ¼è§ģ
    -0.06
    POSITIVE LOGITS
    OMIC
    0.08
    angg
    0.07
    vell
    0.07
    _pow
    0.07
    ucher
    0.07
    åĤħ
    0.07
    nish
    0.07
    æIJľ
    0.07
    anan
    0.07
    ä¹Łå¥½
    0.07
    Activations Density 0.004%

    No Known Activations