© 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. 58375
    Prev
    Next
    INDEX
    Explanations

    parameterized type

    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
     Dahl
    -0.08
    ømm
    -0.07
    ToFit
    -0.07
     SimpleName
    -0.07
     поÑģÑĭ
    -0.07
    estand
    -0.07
    adari
    -0.07
    ager
    -0.07
    urian
    -0.07
    éĹŃéŨ
    -0.07
    POSITIVE LOGITS
    趣
    0.08
    被称为
    0.07
     Hugo
    0.07
    趣åij³
    0.06
    é£İè¡Į
    0.06
    æľĢèijĹåIJįçļĦ
    0.06
     expended
    0.06
    çĮİ
    0.06
    tua
    0.06
    дини
    0.06
    Activations Density 0.150%

    No Known Activations