© 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. 21464
    Prev
    Next
    INDEX
    Explanations

    was or is followed by a noun

    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
    icy
    -0.07
    ded
    -0.07
     catastro
    -0.06
    æķ²
    -0.06
    icz
    -0.06
    pine
    -0.06
     ded
    -0.06
    æľīä»Ģä¹Ī
    -0.06
    ény
    -0.06
    elves
    -0.06
    POSITIVE LOGITS
    aro
    0.07
    æĬĬåŃ©åŃIJ
    0.07
     //-
    0.07
    ëĦIJ리
    0.07
    为åģļ好
    0.07
    nda
    0.07
    achen
    0.07
    oku
    0.07
    TURN
    0.07
    hare
    0.07
    Activations Density 1.093%

    No Known Activations