© 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. 2062
    Prev
    Next
    INDEX
    Explanations

    fragmented text

    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
    rub
    -0.22
     Duis
    -0.21
    èįīåĿª
    -0.21
    dux
    -0.19
    ç½ħ
    -0.18
    ËĪ
    -0.18
     annoy
    -0.18
    èľĴ
    -0.18
     pageTitle
    -0.18
     slapped
    -0.18
    POSITIVE LOGITS
    ãĤıãģĭãģ£ãģ¦
    0.20
    cate
    0.20
    roperties
    0.20
    Ãİ
    0.19
    ç¼±
    0.19
     EXEMPLARY
    0.18
     maneu
    0.18
    pisa
    0.18
    lijah
    0.18
    quil
    0.18
    Activations Density 0.001%

    No Known Activations