© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    legal rules

    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
    ++;č↵č↵
    -0.22
    estruction
    -0.21
    )||(
    -0.20
    ABCDEFGHIJKLMNOP
    -0.20
    @endif
    -0.20
    stateParams
    -0.20
     A
    -0.20
    arhus
    -0.19
     urlString
    -0.19
     B
    -0.19
    POSITIVE LOGITS
    matchCondition
    0.24
    ç½ijé¦ĸ页
    0.22
    _HERSHEY
    0.21
     diseñador
    0.21
    BOSE
    0.21
     negó
    0.20
     earthqu
    0.20
    crast
    0.20
    regor
    0.20
     Dud
    0.20
    Activations Density 0.006%

    No Known Activations