© 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. 64679
    Prev
    Next
    INDEX
    Explanations

    flavonoids

    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
    油水
    -0.07
     Blas
    -0.07
    å¡ijèĥ¶
    -0.06
    佬
    -0.06
     blas
    -0.06
    à²ĸ
    -0.06
    elius
    -0.06
     horns
    -0.06
    andum
    -0.06
    kana
    -0.06
    POSITIVE LOGITS
    uston
    0.08
    reeze
    0.08
    urope
    0.08
    оди
    0.08
     Coimbra
    0.08
    é»Ħéħ®
    0.08
    åĹĸ
    0.08
    æѦéŃĤ
    0.08
    eneric
    0.07
     Frag
    0.07
    Activations Density 0.041%

    No Known Activations