© 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. 50470
    Prev
    Next
    INDEX
    Explanations

    urls or code links

    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
    âĢ¦âĢ¦ãĢĤ
    -0.08
    isFunction
    -0.08
    <|box_end|>
    -0.08
    âĢ¦ãĢĤ
    -0.08
    owski
    -0.08
    fills
    -0.07
    cock
    -0.07
    imbus
    -0.07
    elpers
    -0.07
    ingk
    -0.07
    POSITIVE LOGITS
    https
    0.07
    hti
    0.07
    俱ä¹IJéĥ¨
    0.06
    hini
    0.06
    åĪ©å®³
    0.06
    lu
    0.06
    à¹Ģà¸Ľà¸£
    0.06
    allet
    0.06
     divisive
    0.06
    s
    0.06
    Activations Density 0.047%

    No Known Activations