© 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. 1488
    Prev
    Next
    INDEX
    Explanations

    legal filings

    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
    ummings
    -0.23
    ynthia
    -0.21
     Nack
    -0.21
    FormItem
    -0.20
    RegularExpression
    -0.20
     erotica
    -0.20
    ithe
    -0.20
    éĥ½æľīèĩªå·±
    -0.20
    alien
    -0.19
    nection
    -0.19
    POSITIVE LOGITS
    ðŁ¥ĩ
    0.25
    æĿ¨æ¬¢
    0.25
     practition
    0.23
    æŁ¥çľĭ详æĥħ
    0.23
    áµĴ
    0.22
    代çIJĨ
    0.22
     beÄŁen
    0.21
     firm
    0.21
     (~(
    0.21
     offices
    0.20
    Activations Density 0.789%

    No Known Activations