© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17898
    Prev
    Next
    INDEX
    Explanations

    deficiency shortage turmoil replacement distortion

    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
    yah
    -0.07
    æķĻåѦæķĪæŀľ
    -0.07
     ÙħÙĨÙĩا
    -0.07
    fri
    -0.07
     Response
    -0.07
    vari
    -0.07
    omatic
    -0.07
    uish
    -0.06
    临
    -0.06
    fum
    -0.06
    POSITIVE LOGITS
    imy
    0.08
    çªģçĦ¶
    0.07
    è¶Ĭ
    0.07
    ebra
    0.07
    occo
    0.07
    aing
    0.07
    _PROP
    0.06
    æĦıåij³çĿĢ
    0.06
    æŀī
    0.06
    mena
    0.06
    Activations Density 0.049%

    No Known Activations