© 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. 58279
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and 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
    itano
    -0.08
    ToShow
    -0.07
    ä¸į代表
    -0.07
    ÏģÏį
    -0.07
    >>>>>>>
    -0.07
    asanya
    -0.07
    anu
    -0.07
    ä¸Ģéĥİ
    -0.07
    ĤŃ
    -0.07
    letcher
    -0.07
    POSITIVE LOGITS
    orex
    0.07
    æ®Ĭ
    0.06
    /bit
    0.06
    ropolis
    0.06
    ãĢĤï¼Ī
    0.06
    -bel
    0.06
    ç¾¹
    0.06
    belie
    0.06
    (bit
    0.06
     Budd
    0.06
    Activations Density 0.004%

    No Known Activations