© 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. 113
    Prev
    Next
    INDEX
    Explanations

    Each

    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
     altogether
    -0.22
     all
    -0.21
    å¦Ĥæľīä¾µæĿĥ
    -0.21
    2
    -0.20
     various
    -0.20
    åIJĦç§į
    -0.20
    大家åı¯ä»¥
    -0.20
    ruz
    -0.19
    å¦Ĥæŀľä¸įæĺ¯
    -0.19
     observ
    -0.19
    POSITIVE LOGITS
     individually
    0.41
     individual
    0.40
    ë§Īëĭ¤
    0.37
    individual
    0.37
    éĥ½æľīèĩªå·±
    0.34
    åįķçĭ¬
    0.34
     einzel
    0.31
     اÙĦÙĪاØŃد
    0.30
     respective
    0.30
    Individual
    0.29
    Activations Density 1.118%

    No Known Activations