© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    analysis and management

    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
    æĸĩåĮĸä¼łåªĴ
    -0.24
    æ¦Ĥ念èĤ¡
    -0.24
     @$_
    -0.23
    $MESS
    -0.22
     Erotic
    -0.21
    称ä¹ĭ
    -0.21
    ProcessEvent
    -0.20
    /the
    -0.20
    CardContent
    -0.20
    -Jul
    -0.20
    POSITIVE LOGITS
     the
    0.31
     them
    0.30
    äºĨ好
    0.28
    esteem
    0.27
    äºĨåįĬ天
    0.27
    äºĨ
    0.26
    äºĨ许å¤ļ
    0.26
    äºĨä¸įå°ij
    0.25
    å¾Ĺå¾Ī好
    0.25
    äºĨåĩł
    0.25
    Activations Density 5.459%

    No Known Activations