© 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. 3797
    Prev
    Next
    INDEX
    Explanations

    boolean or is

    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
    akening
    -0.23
    slaught
    -0.22
    esktop
    -0.21
     HeaderComponent
    -0.21
    rı
    -0.21
     Pornhub
    -0.21
    getStore
    -0.21
    .compareTo
    -0.21
    ounter
    -0.20
    æ±Ĩ
    -0.20
    POSITIVE LOGITS
    .vaadin
    0.26
    éľĢè¦ģçĶ¨
    0.23
     XCTAssertTrue
    0.22
    _Framework
    0.21
     newInstance
    0.21
    FromNib
    0.21
    \grid
    0.20
    æĪijè®°å¾Ĺ
    0.20
     need
    0.20
     Prefer
    0.20
    Activations Density 0.112%

    No Known Activations