© 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. 2131
    Prev
    Next
    INDEX
    Explanations

    difficult situations

    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
    .WriteByte
    -0.21
    纰
    -0.21
    BorderColor
    -0.19
    toi
    -0.19
    :animated
    -0.19
    )init
    -0.19
    joy
    -0.19
    afx
    -0.19
    umed
    -0.19
    =./
    -0.19
    POSITIVE LOGITS
    â¬ĩ
    0.22
    <bits
    0.21
    ãĥµ
    0.21
    彧
    0.21
    ':''
    0.20
    åĻĮ
    0.20
    ðŁijĩ
    0.20
     RequestOptions
    0.19
     Oczy
    0.19
     AuthenticationService
    0.19
    Activations Density 2.121%

    No Known Activations