© 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. 303
    Prev
    Next
    INDEX
    Explanations

    Category

    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
    âļĹ
    -0.34
    "<?
    -0.31
    âĴ¸
    -0.29
    <quote
    -0.28
    âĮĤ
    -0.28
    istring
    -0.26
    ðŁĵIJ
    -0.26
     Clintons
    -0.25
    ðŁ¥ĩ
    -0.25
    ">//
    -0.25
    POSITIVE LOGITS
    :
    0.31
    }č↵č↵č↵č↵
    0.22
     offsetof
    0.20
     "";č↵č↵
    0.20
     members
    0.19
     strstr
    0.19
    ç¬ŀ
    0.19
     Ð
    0.19
     member
    0.18
    éĻ¢åŃIJ
    0.18
    Activations Density 0.153%

    No Known Activations