© 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. 1460
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    noinspection
    -0.23
    }elseif
    -0.21
    ="__
    -0.21
    çļĦä¸ĢåĪĩ
    -0.21
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.21
    âĺŁ
    -0.20
    \Carbon
    -0.20
    è¿ĶåĽŀæIJľçĭIJ
    -0.20
    缸è¿ij
    -0.19
     RaycastHit
    -0.19
    POSITIVE LOGITS
     matter
    0.28
    ä¸ĢåĽŀäºĭ
    0.27
    å½ĵä¹ĭæĹłæĦ§
    0.26
    ujet
    0.26
     unto
    0.25
    ç»ĦæĪIJéĥ¨åĪĨ
    0.25
     part
    0.24
    åĽŀäºĭ
    0.24
     testament
    0.24
    çļĦä¸Ģéĥ¨åĪĨ
    0.23
    Activations Density 3.442%

    No Known Activations