© 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. 18870
    Prev
    Next
    INDEX
    Explanations

    ionic states, nuclear relaxation, cavity properties

    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
    åIJįåī¯åħ¶å®ŀ
    -0.07
     okaz
    -0.07
    XObject
    -0.07
    <|box_end|>
    -0.07
    /lists
    -0.07
    esti
    -0.07
    estig
    -0.07
    =log
    -0.07
    icao
    -0.07
    ä¼¼æĺ¯
    -0.07
    POSITIVE LOGITS
    /
    0.08
    -to
    0.08
    -only
    0.07
    -specific
    0.07
    reh
    0.07
    olk
    0.07
    olem
    0.07
    -centric
    0.07
    ino
    0.07
    -side
    0.07
    Activations Density 0.096%

    No Known Activations