© 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. 2379
    Prev
    Next
    INDEX
    Explanations

    instructions and advice

    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
     This
    -0.21
     Vale
    -0.20
    æĥħæĻ¯
    -0.20
    nie
    -0.19
    lands
    -0.19
    亲çĪ±
    -0.19
     credits
    -0.18
     Ñģобой
    -0.18
    è°¨
    -0.18
    soever
    -0.18
    POSITIVE LOGITS
    åı¦ä¸Ģ个
    0.25
    @brief
    0.24
    æĹ¢çĦ¶
    0.24
    ï¼ł
    0.24
     next
    0.23
    éĻ¤äºĨ
    0.22
    ï¼ģ');↵
    0.22
    phalt
    0.22
    ä¸ĭä¸ĢæŃ¥
    0.22
    "text
    0.21
    Activations Density 0.110%

    No Known Activations