© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3883
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    _userid
    -0.19
     ord
    -0.19
    éľ²å¤©
    -0.19
     )->
    -0.18
     drv
    -0.18
     uns
    -0.18
    "go
    -0.18
     swiper
    -0.18
    è¿Ļä½į
    -0.18
     gun
    -0.18
    POSITIVE LOGITS
    rawid
    0.27
    #af
    0.26
    ilogy
    0.24
     safeg
    0.23
    .iOS
    0.23
    åı¯æĥ³èĢĮ
    0.22
    htags
    0.22
    (iOS
    0.22
    @dynamic
    0.22
     (~(
    0.22
    Activations Density 0.001%

    No Known Activations