© 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. 1733
    Prev
    Next
    INDEX
    Explanations

    side effects

    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
    åħħè£ķ
    -0.23
    çĹħåĽł
    -0.22
    ijIJ
    -0.21
    \htdocs
    -0.20
    æĤ£æľī
    -0.20
    activo
    -0.20
    å·®è·Ŀ
    -0.20
    æºIJæ³ī
    -0.20
    ombo
    -0.19
    好åIJ§
    -0.19
    POSITIVE LOGITS
    åī¯ä½ľçĶ¨
    0.34
    /↵↵↵↵
    0.32
     effects
    0.27
    åī¯
    0.26
    swire
    0.25
     */↵↵↵↵
    0.25
     side
    0.24
     lasting
    0.24
    -FIRST
    0.23
    )){↵↵
    0.23
    Activations Density 2.690%

    No Known Activations