© 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. 27976
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code

    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
    ovina
    -0.08
    oplan
    -0.08
    relevant
    -0.07
    ä¸Ģç¬ij
    -0.07
    ugg
    -0.07
    Plan
    -0.07
    åIJŀåĻ¬
    -0.07
    çļĦåį±å®³
    -0.07
    éo
    -0.07
    æŃ¤æ¥¼
    -0.07
    POSITIVE LOGITS
    NT
    0.07
    nts
    0.07
    Cop
    0.06
    æ¡
    0.06
     NT
    0.06
    สะ
    0.06
    ãĤ®ãĥ¼
    0.06
    Å¡ek
    0.06
    ç£ĭ
    0.06
    egy
    0.06
    Activations Density 0.001%

    No Known Activations