© 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. 9173
    Prev
    Next
    INDEX
    Explanations

    1/x

    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
    onz
    -0.08
    rint
    -0.07
    ÑĢек
    -0.07
    iedere
    -0.07
    ?v
    -0.07
    tesy
    -0.07
    åĽ½åįİ
    -0.06
    欲滴
    -0.06
    imbang
    -0.06
    ostar
    -0.06
    POSITIVE LOGITS
    åĴĮæĶ¹åĸĦ
    0.08
    raid
    0.07
    ¶ļ
    0.07
    chain
    0.06
    itude
    0.06
    alt
    0.06
    å°±æĢķ
    0.06
    иÑģÑĤÑĢа
    0.06
    inite
    0.06
    izable
    0.06
    Activations Density 0.016%

    No Known Activations