© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    methods and novel

    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
    çļĦæ¨¡æł·
    -0.23
    retweeted
    -0.20
    longleftrightarrow
    -0.20
    licher
    -0.19
    éĹ¾
    -0.19
    \widgets
    -0.19
    çļĦä¸ĢéĿ¢
    -0.19
    ):?>↵
    -0.18
    bies
    -0.18
    @Setter
    -0.18
    POSITIVE LOGITS
    æĸ¹æ³ķ
    0.27
    çļĦæĸ¹æ³ķ
    0.27
     method
    0.26
    addtogroup
    0.26
     novel
    0.25
     methods
    0.25
    nqu
    0.25
     æĸ¹æ³ķ
    0.24
    æľ¬
    0.23
     addCriterion
    0.23
    Activations Density 1.513%

    No Known Activations