© 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. 1769
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     typingsSlinky
    -0.26
     typingsJapgolly
    -0.25
    åIJįåĪĹåīį
    -0.24
    ä»İæł¹æľ¬
    -0.24
    大大å°ı
    -0.22
    å¿ħä¸įåı¯
    -0.22
    æģ¯æģ¯
    -0.21
    è°ĭæ±Ĥ
    -0.20
     Rencontres
    -0.20
    à¸łà¸²à¸§
    -0.20
    POSITIVE LOGITS
    ();)
    0.30
    orgeous
    0.28
    phinx
    0.27
     CircularProgress
    0.25
    endir
    0.25
    âĨ¤
    0.25
    nqu
    0.24
    ,$_
    0.24
    ðŁijĭ
    0.24
    -www
    0.24
    Activations Density 2.004%

    No Known Activations