© 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. 46708
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Hôtel
    -0.23
    =\"$
    -0.23
    åĭł
    -0.23
    çĶ¨å¾®ä¿¡
    -0.22
    èĤĦ
    -0.22
    POWER
    -0.22
    é¢ĺ主
    -0.21
    âĺĢ
    -0.21
    é³Į
    -0.21
    è¶ĬæĿ¥è¶Ĭ好
    -0.21
    POSITIVE LOGITS
    ãģķãģ¾ãģĸãģ¾
    0.26
    -Trump
    0.24
    -abortion
    0.24
    æ§ĺãĢħ
    0.23
    antt
    0.22
    erre
    0.21
     asses
    0.20
    uars
    0.20
    entiful
    0.20
     Readonly
    0.20
    Activations Density 0.124%

    No Known Activations