© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 290
    Prev
    Next
    INDEX
    Explanations

    is/are

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceipt
    -0.23
    NgModule
    -0.23
    );">↵
    -0.23
    ç²¾çĽĬæ±Ĥ
    -0.22
    gom
    -0.21
    åīįæīĢæľªæľī
    -0.20
    _asm
    -0.20
    游æĪıæĬĢå·§
    -0.20
    åIJįåĪĹåīį
    -0.20
    gomery
    -0.19
    POSITIVE LOGITS
     often
    0.38
     widely
    0.33
    eldom
    0.32
    ç»ı常
    0.32
     frequently
    0.31
    æĻ®éģį
    0.31
     commonly
    0.31
     generally
    0.30
     among
    0.29
    常
    0.28
    Activations Density 7.298%

    No Known Activations