© 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. 24829
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
    är
    -0.07
    æīĵèµ·
    -0.06
     marginal
    -0.06
    åĴĮæĻ®éĢļ
    -0.06
    ove
    -0.06
    纹
    -0.06
    ovice
    -0.06
    ád
    -0.06
    зол
    -0.06
     arche
    -0.06
    POSITIVE LOGITS
    ican
    0.08
    зво
    0.08
    ||(
    0.07
    èµĸ
    0.07
    acor
    0.07
    igel
    0.07
    wak
    0.07
    èĤĨæĹłå¿Į
    0.07
    lieben
    0.07
    å°ijåħĪ
    0.07
    Activations Density 0.101%

    No Known Activations