© 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. 338
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
     masturbating
    -0.26
    oire
    -0.22
    egov
    -0.21
    eeper
    -0.20
    prites
    -0.20
    NotSupportedException
    -0.19
    amel
    -0.19
    modele
    -0.19
    isObject
    -0.19
    é³ľ
    -0.19
    POSITIVE LOGITS
    éĥħ
    0.20
    éªĮ
    0.20
    çļĦä¸ĢéĿ¢
    0.18
    __':č↵
    0.18
     ÑĢаÑģÑĤв
    0.18
     bindActionCreators
    0.18
    红åĪ©
    0.18
    çıħ
    0.18
    纪æ£Ģ
    0.18
    Bal
    0.18
    Activations Density 0.003%

    No Known Activations