© 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. 3815
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ().'/
    -0.24
    AccessException
    -0.21
     localVar
    -0.21
    recision
    -0.19
     suche
    -0.19
    >*</
    -0.19
    ModelProperty
    -0.18
    éĢł
    -0.18
    getY
    -0.18
    éĵ¨
    -0.18
    POSITIVE LOGITS
    éĢħ
    0.24
    æ¹ī
    0.24
    çļĽ
    0.23
    ä»ī
    0.22
    嬿
    0.22
     JADX
    0.21
    婳
    0.21
    _WS
    0.21
    :disable
    0.21
    âĩ¨
    0.21
    Activations Density 0.281%

    No Known Activations