© 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. 28592
    Prev
    Next
    INDEX
    Explanations

    academic paper abstracts

    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
    åįµçŁ³
    -0.08
    淤泥
    -0.08
    atura
    -0.08
    iane
    -0.07
    è¿·æĥij
    -0.07
    #${
    -0.07
    ToAdd
    -0.07
    å¤ķ
    -0.07
    asury
    -0.07
    ffffffff
    -0.07
    POSITIVE LOGITS
     abstract
    0.09
    abstract
    0.09
    Keywords
    0.09
     Abstract
    0.08
    doi
    0.08
     Keywords
    0.08
     research
    0.08
    çłĶ究äºĨ
    0.08
    åħ³éĶ®è¯į
    0.07
     investigation
    0.07
    Activations Density 0.773%

    No Known Activations