© 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. 1735
    Prev
    Next
    INDEX
    Explanations

    code framework syntax

    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
    è¦ģä¸įçĦ¶
    -0.25
     airstrikes
    -0.24
    娱ä¹IJåľĪ
    -0.24
    æĹ¶ä»£ä¸ŃåĽ½
    -0.20
     dolore
    -0.20
    routeProvider
    -0.20
     eng
    -0.20
     ÑģоÑĩеÑĤа
    -0.20
    @Configuration
    -0.20
    çļĦ带é¢Ĩ
    -0.19
    POSITIVE LOGITS
    ¡´
    0.36
    économ
    0.27
    :CGRect
    0.26
    <Scalar
    0.26
    -REAL
    0.24
    ±ħ
    0.24
     subparagraph
    0.24
    bsolute
    0.23
    åī¯åİ¿éķ¿
    0.23
    æĿ¨æ¬¢
    0.23
    Activations Density 2.354%

    No Known Activations