© 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. 56791
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    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
    noz
    -0.09
    aggio
    -0.08
    æľīæĦıä¹ī
    -0.08
    klen
    -0.08
    ataka
    -0.08
    igde
    -0.07
    åĩ¡æľ¬ç½ij注æĺİ
    -0.07
     Meadows
    -0.07
    -muted
    -0.07
    roller
    -0.07
    POSITIVE LOGITS
    ä»ĺ诸
    0.10
    åľ¨åħ·ä½ĵ
    0.09
    å®ŀæĵį
    0.09
     konkret
    0.09
     accordingly
    0.09
     concrete
    0.09
     konkrete
    0.09
    åħ·ä½ĵçļĦ
    0.09
     practical
    0.08
    å®ŀéĻħè¡ĮåĬ¨
    0.08
    Activations Density 0.556%

    No Known Activations