© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    identifiers or metadata

    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
    <small
    -0.23
    ðŁijĭ
    -0.20
    viewController
    -0.20
    có
    -0.19
     HOR
    -0.19
    **/↵
    -0.19
    iết
    -0.19
    agged
    -0.19
    acades
    -0.18
    èĪª
    -0.18
    POSITIVE LOGITS
    å°ıç¼ĸä¸Ģèµ·
    0.20
    游æĪıè§Ĵèī²
    0.20
    idle
    0.19
    æ¹İ
    0.19
     idle
    0.19
    Idle
    0.19
    ,buf
    0.19
    åIJĪ并
    0.19
    é»ijæģ¶åĬ¿åĬĽ
    0.18
    _IDLE
    0.18
    Activations Density 0.001%

    No Known Activations