© 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. 2673
    Prev
    Next
    INDEX
    Explanations

    Version

    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
    apult
    -0.27
    gnore
    -0.24
    izabeth
    -0.23
     ÑģенÑĤ
    -0.23
    rtle
    -0.23
    washer
    -0.23
    __;
    -0.23
    çĶ¸
    -0.22
     ViewChild
    -0.22
    akest
    -0.22
    POSITIVE LOGITS
    OrCreate
    0.23
    é¾ĩ
    0.22
    ToFront
    0.22
    ç¡Į
    0.22
     qed
    0.22
    è£Ĩ
    0.22
    readcrumbs
    0.21
    æIJ½
    0.20
    .getInteger
    0.20
    ablish
    0.20
    Activations Density 0.148%

    No Known Activations