© 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. 63392
    Prev
    Next
    INDEX
    Explanations

    brief introduction or explanation

    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
    frey
    -0.10
    bject
    -0.09
    /her
    -0.09
    ê¼Ń
    -0.09
    arity
    -0.08
    áĢ·
    -0.08
    bserv
    -0.08
    hlen
    -0.08
    omb
    -0.08
    mega
    -0.08
    POSITIVE LOGITS
    ly
    0.13
     جدÙĭا
    0.10
    est
    0.10
    ely
    0.09
     جداÙĭ
    0.09
    ening
    0.08
    ÃŃsimo
    0.08
    íŀĪ
    0.08
    ãĥ¥
    0.08
    fristig
    0.08
    Activations Density 0.016%

    No Known Activations