© 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. 910
    Prev
    Next
    INDEX
    Explanations

    Q and Pro

    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
    çĤĿ
    -0.25
    ?("
    -0.21
    åıĺæĢģ
    -0.20
     "','
    -0.20
     IMPLIED
    -0.20
    æį¢åı¥è¯Ŀ
    -0.19
    KV
    -0.18
    ç«ĭãģ¡
    -0.18
    ););↵
    -0.18
    TW
    -0.18
    POSITIVE LOGITS
    çİŁ
    0.23
     Depths
    0.22
     rencont
    0.21
    uesto
    0.20
    èĽ©
    0.20
    orthand
    0.19
    .execSQL
    0.19
    crast
    0.19
    è£ĺ
    0.19
     Forge
    0.19
    Activations Density 0.001%

    No Known Activations