© 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. 432
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
    omanip
    -0.24
     beÄŁen
    -0.24
    rvine
    -0.23
    RuntimeObject
    -0.22
    éta
    -0.22
    HeaderCode
    -0.21
     escorte
    -0.21
    estroy
    -0.20
    ieme
    -0.20
    icap
    -0.20
    POSITIVE LOGITS
    mÃ¤ÃŁig
    0.21
    壶
    0.21
    éªĸ
    0.20
    QUIRED
    0.20
    çı
    0.19
    ãİı
    0.18
    hall
    0.18
    /loader
    0.18
    fast
    0.18
    åľ°æ®µ
    0.18
    Activations Density 0.002%

    No Known Activations