© 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. 2346
    Prev
    Next
    INDEX
    Explanations

    vice

    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
    -Compatible
    -0.29
    /Instruction
    -0.27
    (*)(
    -0.26
    peria
    -0.26
    nicos
    -0.25
    -Cs
    -0.24
    ",[
    -0.23
    )'),
    -0.23
    akest
    -0.22
    anax
    -0.22
    POSITIVE LOGITS
     vice
    0.27
     Vice
    0.24
     cont
    0.23
    åıįè¿ĩæĿ¥
    0.23
    糣
    0.22
    é¢ł
    0.21
    æijĨåľ¨
    0.20
    eway
    0.20
    oji
    0.19
    读åIJİ
    0.19
    Activations Density 0.126%

    No Known Activations