© 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. 2282
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Ļ¶
    -0.23
    illow
    -0.21
    %%%%%%%%%%%%%%%%
    -0.19
    æĬĬè¿Ļ个
    -0.19
     butterknife
    -0.19
     stiff
    -0.19
    .opend
    -0.19
    ()."
    -0.19
     )}↵↵
    -0.19
    .liferay
    -0.18
    POSITIVE LOGITS
    abbix
    0.22
    åľ°æ®µ
    0.22
     Paginator
    0.21
    StrictEqual
    0.21
    enate
    0.21
    VERR
    0.21
    ÑĦÑĦ
    0.20
    (Roles
    0.19
    metros
    0.19
    潦
    0.19
    Activations Density 0.155%

    No Known Activations