© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 974
    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
    matchCondition
    -0.23
    ¬ģ
    -0.22
    pherd
    -0.21
    çŀŁ
    -0.19
    åijĶ
    -0.19
    _usec
    -0.19
    _NONNULL
    -0.19
    éĻī
    -0.19
    æijĩäºĨ
    -0.19
    utf
    -0.18
    POSITIVE LOGITS
    },č↵č↵
    0.23
    antor
    0.23
    ouser
    0.23
    åľ¨ä¼łå¥ĩ
    0.22
    ;!
    0.22
    åľ¨çݩ家ä¸Ń
    0.21
    ,Th
    0.21
    twor
    0.21
    "class
    0.21
    ãģ¦ãģĹãģ¾ãģ£ãģ¦
    0.21
    Activations Density 0.399%

    No Known Activations