© 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. 42222
    Prev
    Next
    INDEX
    Explanations

    specific language fragments

    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
    erty
    -0.08
    ison
    -0.07
    ety
    -0.07
    izon
    -0.07
    iture
    -0.07
    uct
    -0.07
    ogy
    -0.07
    esis
    -0.07
    2
    -0.07
    ÑĤоÑĢ
    -0.07
    POSITIVE LOGITS
    à¹Į
    0.10
    ystems
    0.10
    chedulers
    0.09
    à°¨à±įని
    0.09
    æŁ¥çľĭåħ¨éĥ¨
    0.08
    åįķä½įåıĤåĬł
    0.08
    geführ
    0.08
    creens
    0.08
    etje
    0.08
    ervices
    0.08
    Activations Density 0.146%

    No Known Activations