© 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-65K
    7. 2577
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    ç¡ļ
    -0.21
     démarch
    -0.20
    _VOID
    -0.20
    âĢ½
    -0.19
    SFML
    -0.19
    ÙħÙĬد
    -0.19
    è°Ł
    -0.19
    æŀĦ
    -0.19
     ResourceType
    -0.19
    åıijå±ķ壮大
    -0.18
    POSITIVE LOGITS
    å°ıç¼ĸä¸Ģèµ·
    0.24
    ëijł
    0.23
    å§Ķç»Ħç»ĩ
    0.21
    são
    0.20
    lli
    0.20
    Å»
    0.19
    ç¦ļ
    0.19
    ilogy
    0.19
     Instit
    0.19
     MetroFramework
    0.19
    Activations Density 0.006%

    No Known Activations