© 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-CHAT-65K
    7. 46183
    Prev
    Next
    INDEX
    Explanations

    waking up

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨éĩĮéĿ¢
    -0.27
    åľ¨éĤ£éĩĮ
    -0.26
     Ja
    -0.24
    åĪ°è¿ĻéĩĮ
    -0.23
     typingsSlinky
    -0.23
    PO
    -0.22
    Nguá»ĵn
    -0.21
    è¿ĽæĿ¥
    -0.21
    arium
    -0.20
    UME
    -0.20
    POSITIVE LOGITS
    iked
    0.22
    åĩºçİ°åľ¨
    0.22
    ambi
    0.21
    ünc
    0.21
    娱ä¹IJå¹³åı°
    0.20
    SessionFactory
    0.19
     ());↵↵
    0.19
    ogie
    0.18
     Sweep
    0.18
    ycop
    0.18
    Activations Density 0.125%

    No Known Activations