© 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. 57875
    Prev
    Next
    INDEX
    Explanations

    mathematical function evaluation

    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
    ountain
    -0.08
    iland
    -0.08
     Makan
    -0.08
    schau
    -0.07
    alore
    -0.07
    illions
    -0.07
     übern
    -0.07
    æľįä»İ
    -0.07
    éħĹ
    -0.07
    ottom
    -0.07
    POSITIVE LOGITS
    æķĻäºİ
    0.07
    eger
    0.07
    iez
    0.07
     ÙĪعÙĨد
    0.07
    Ùĥب
    0.06
    è¾Ĺ
    0.06
    åħ¥åı£å¤Ħ
    0.06
    _finder
    0.06
    å½ĵä¹ĭ
    0.06
    ATAL
    0.06
    Activations Density 0.028%

    No Known Activations