© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions containing variables

    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
    /print
    -0.08
    éŀ
    -0.07
    åī¯ä¸»å¸Ń
    -0.07
    edar
    -0.07
    edom
    -0.07
    waan
    -0.06
     Mant
    -0.06
    bog
    -0.06
    wear
    -0.06
    ikle
    -0.06
    POSITIVE LOGITS
    rum
    0.07
    çļĦä¸ĢåįĬ
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
    OfString
    0.07
    onds
    0.07
    abis
    0.06
    éĩijå±±
    0.06
    ABL
    0.06
    Half
    0.06
    veh
    0.06
    Activations Density 0.005%

    No Known Activations