© 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. 486
    Prev
    Next
    INDEX
    Explanations

    code/technical words

    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
    .offsetHeight
    -0.22
    ptive
    -0.20
    OSH
    -0.20
    WithMany
    -0.20
    è®°èĢħäºĨ解
    -0.20
    obutton
    -0.19
    _FUNC
    -0.19
    颤
    -0.19
    .jasper
    -0.19
    ighton
    -0.19
    POSITIVE LOGITS
     createState
    0.26
     Türkiye
    0.24
    entes
    0.22
    eph
    0.22
    ðŁijĭ
    0.21
    --*/↵
    0.20
    strstr
    0.20
    สย
    0.20
    yna
    0.19
     Disqus
    0.19
    Activations Density 1.572%

    No Known Activations