© 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. 63299
    Prev
    Next
    INDEX
    Explanations

    minimal, simplest, smallest, maximal

    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
    orado
    -0.08
    ibert
    -0.08
    essar
    -0.08
    _like
    -0.08
    agher
    -0.08
    oret
    -0.07
    IDD
    -0.07
    elius
    -0.07
    terer
    -0.07
    utto
    -0.07
    POSITIVE LOGITS
    IMUM
    0.07
    imum
    0.07
    (min
    0.07
    åĴĮæľĢ
    0.07
    èµ·è§ģ
    0.07
    à¸Ĺีà¹Īสุà¸Ķ
    0.07
    è¦ĥ
    0.07
    /root
    0.06
    ä¹Łæĺ¯æľĢ
    0.06
     span
    0.06
    Activations Density 0.012%

    No Known Activations