© 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. 26259
    Prev
    Next
    INDEX
    Explanations

    combining words and combinations

    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
    bre
    -0.06
    .ny
    -0.06
     implicitly
    -0.06
     assumed
    -0.06
     Ny
    -0.06
    tiny
    -0.06
    å°½åľ¨
    -0.06
     ap
    -0.06
     H
    -0.06
     species
    -0.06
    POSITIVE LOGITS
     kombin
    0.10
     kombinasi
    0.10
     комбина
    0.09
     combos
    0.09
     combinaison
    0.09
     combinations
    0.09
     combinación
    0.08
    รัมยà¹Į
    0.08
     combination
    0.08
    è¯ķè¯ķ
    0.08
    Activations Density 0.002%

    No Known Activations