© 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. 2058
    Prev
    Next
    INDEX
    Explanations

    support and answers

    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
    .epam
    -0.22
    èī¨
    -0.21
    }elseif
    -0.21
    ]init
    -0.21
    :numel
    -0.20
    grese
    -0.20
    arium
    -0.19
    ðŁĵIJ
    -0.19
    .lesson
    -0.19
    دÙĬÙĨ
    -0.19
    POSITIVE LOGITS
    解çŃĶ
    0.36
    çŃĶçĸij
    0.32
     troubleshooting
    0.29
    åĽŀçŃĶ
    0.29
    æ±ĤåĬ©
    0.29
     answer
    0.29
     answers
    0.28
    解åĨ³éĹ®é¢ĺ
    0.28
    çĸijéļ¾
    0.28
     support
    0.27
    Activations Density 0.454%

    No Known Activations