© 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. 3437
    Prev
    Next
    INDEX
    Explanations

    website page context

    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
    :'.$
    -0.32
    :".$
    -0.26
    ðŁĺĤ
    -0.24
    ().'/
    -0.23
     nuest
    -0.23
    phalt
    -0.22
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.22
    ðŁĺģ
    -0.22
    apgolly
    -0.22
    eÄŁ
    -0.22
    POSITIVE LOGITS
     ext
    0.21
     straw
    0.20
     tab
    0.19
    et
    0.19
     [
    0.19
    ế
    0.19
    .Gravity
    0.18
    .Autowired
    0.18
    ç¿ĥ
    0.18
     George
    0.18
    Activations Density 0.940%

    No Known Activations