© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14270
    Prev
    Next
    INDEX
    Explanations

    third derivative

    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
    åħļåĴĮ人æ°ij
    -0.08
    nies
    -0.07
    管å±Ģ
    -0.07
    æķħäºĭæĥħ
    -0.07
    emps
    -0.07
    arges
    -0.07
    enville
    -0.07
    çªģ
    -0.06
    aih
    -0.06
    olat
    -0.06
    POSITIVE LOGITS
    ucci
    0.07
    adj
    0.07
    isir
    0.07
    chez
    0.07
    :g
    0.06
    çĪ½
    0.06
     imb
    0.06
    åĮ¹
    0.06
    Ñĩки
    0.06
    åŃľ
    0.06
    Activations Density 0.083%

    No Known Activations