© 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. 3197
    Prev
    Next
    INDEX
    Explanations

    had + verb

    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
    <|box_end|>
    -0.11
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    -0.09
    Ùĩ
    -0.09
    ighbors
    -0.09
    о
    -0.09
    gerald
    -0.09
    bial
    -0.09
    ела
    -0.09
    еÑģÑĤа
    -0.09
    scious
    -0.08
    POSITIVE LOGITS
    zelfde
    0.14
    ت
    0.13
    t
    0.09
    ronic
    0.09
    е
    0.09
    istribution
    0.09
    erness
    0.08
    qiq
    0.08
    rive
    0.08
     auparavant
    0.08
    Activations Density 0.102%

    No Known Activations