© 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. 509
    Prev
    Next
    INDEX
    Explanations

    citations and headings

    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
    {Name
    -0.22
    rador
    -0.22
    nemonic
    -0.21
    并ä¸įæĺ¯å¾Ī
    -0.21
     contingent
    -0.20
    ivid
    -0.20
    @update
    -0.19
    -initialized
    -0.19
    OrCreate
    -0.19
    reib
    -0.18
    POSITIVE LOGITS
    ãĥµ
    0.32
    OTOS
    0.25
    _rwlock
    0.22
    åİŁæĸĩåľ°åĿĢ
    0.22
    [at
    0.21
    _SRV
    0.20
    à¹Ĥà¸Ĺษ
    0.20
    .nih
    0.19
    èµī
    0.19
    IRTUAL
    0.19
    Activations Density 0.441%

    No Known Activations