© 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. 2390
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    'icon
    -0.21
    icie
    -0.21
    nqu
    -0.20
     Benghazi
    -0.20
    .ogg
    -0.19
    ophon
    -0.19
     fick
    -0.19
    ļ
    -0.19
    æ°Ľ
    -0.19
    ihn
    -0.19
    POSITIVE LOGITS
    éĶ¨
    0.23
    ABCDEFGHI
    0.23
    ENCED
    0.23
    @Resource
    0.22
    :@""
    0.20
    çİ©ç¬ij
    0.20
    olated
    0.19
    ().'/
    0.19
    é¹Ĥ
    0.19
    (suite
    0.19
    Activations Density 0.001%

    No Known Activations