© 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. 9014
    Prev
    Next
    INDEX
    Explanations

    a number of

    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
    Ùĩ
    -0.10
    angsa
    -0.08
    ש×IJ
    -0.08
    γε
    -0.07
    jenigen
    -0.07
    pedia
    -0.07
    efeller
    -0.07
    enhagen
    -0.07
    ed
    -0.06
    angu
    -0.06
    POSITIVE LOGITS
     dozen
    0.08
     Utre
    0.08
    éĥ¨ä»½
    0.08
    iy
    0.08
     whopping
    0.08
    orta
    0.07
    .o
    0.07
    ÙıÙĨ
    0.07
    qid
    0.07
    ä¸įçķĻ
    0.07
    Activations Density 1.595%

    No Known Activations