© 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. 2998
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
    ']!='
    -0.22
     nonzero
    -0.22
    ]!='
    -0.22
     Politico
    -0.21
    .isNotEmpty
    -0.21
    obook
    -0.20
    avaÅŁ
    -0.20
    ï¼ģ",
    -0.20
    alleries
    -0.20
    nen
    -0.20
    POSITIVE LOGITS
    /Dk
    0.22
    å½ĵä¹ĭ
    0.22
    matchCondition
    0.21
    :CGRect
    0.20
    FunctionFlags
    0.20
    éĶĵ
    0.20
    å°ıç¼ĸä¸Ģèµ·
    0.20
    (strcmp
    0.20
    ä¹ĭåħ§å®¹
    0.20
    .onNext
    0.20
    Activations Density 0.149%

    No Known Activations