© 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. 8426
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and conditions

    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
    RITE
    -0.08
    åľ¨å·¥ä½ľä¸Ĭ
    -0.08
    linger
    -0.08
    ETTI
    -0.08
    ite
    -0.08
     пое
    -0.08
    iten
    -0.08
    lector
    -0.07
    itkan
    -0.07
    bacher
    -0.07
    POSITIVE LOGITS
    çľ
    0.07
    amel
    0.07
    пÑĥÑģÑĤ
    0.07
     Aire
    0.07
    çĦ¡éĻIJ
    0.06
    çķĮçļĦ
    0.06
    æ´ŀ
    0.06
    ely
    0.06
     limitless
    0.06
     flair
    0.06
    Activations Density 0.004%

    No Known Activations