© 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. 316
    Prev
    Next
    INDEX
    Explanations

    wanting

    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
    æĸ°æµªè´¢ç»ı
    -0.31
    ç¾İåªĴ
    -0.29
    ynchronously
    -0.27
    letics
    -0.26
    ðŁļ©
    -0.26
    amework
    -0.26
    ?"↵↵↵↵
    -0.25
    rikes
    -0.25
    thinkable
    -0.25
    ---</
    -0.25
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.34
    -
    0.26
    ↵
    0.25
    /
    0.24
    å·²ä¹ħ
    0.24
    /h
    0.24
     Gran
    0.23
    ,
    0.23
    åĭĥåĭĥ
    0.22
    äºĨè§£æĽ´å¤ļ
    0.21
    Activations Density 3.550%

    No Known Activations