© 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. 7428
    Prev
    Next
    INDEX
    Explanations

    growth, transformations, nowadays, expert, nutrition, campaigns, analysed

    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
     Portions
    -0.10
    vistas
    -0.08
    /WebAPI
    -0.08
     keyed
    -0.08
     ostensibly
    -0.08
    Defaults
    -0.08
    Across
    -0.08
     frustra
    -0.08
     seques
    -0.08
    ickle
    -0.08
    POSITIVE LOGITS
    ´s
    0.11
     nowadays
    0.10
    ´
    0.10
     firstly
    0.09
     Nowadays
    0.09
     significative
    0.09
     splitted
    0.09
    0.09
    igth
    0.09
     Moreover
    0.08
    Activations Density 10.182%

    No Known Activations