© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3971
    Prev
    Next
    INDEX
    Explanations

    confusion and clarity

    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
    DialogTitle
    -0.23
    erea
    -0.22
    ([]);↵↵
    -0.21
    _aspect
    -0.19
    _KeyPress
    -0.19
    ("{\"
    -0.19
    åŁĤ
    -0.19
    .parts
    -0.19
    pdo
    -0.18
    è¹ģ
    -0.18
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.42
    ä¸įæ¸ħæ¥ļ
    0.30
     confusing
    0.29
    æ··ä¹±
    0.29
     unclear
    0.28
     confusion
    0.28
     clarified
    0.27
    模ç³Ĭ
    0.26
     cleared
    0.26
     confuse
    0.26
    Activations Density 0.283%

    No Known Activations