© 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. 456
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
    InMillis
    -0.23
    etter
    -0.22
    anchise
    -0.20
    лев
    -0.20
     înt
    -0.20
    elmet
    -0.19
    ivitÃł
    -0.19
    ccoli
    -0.19
    ennifer
    -0.19
    ä½ľ
    -0.18
    POSITIVE LOGITS
    <?↵
    0.25
    !";č↵
    0.24
    íĶĦë¡ľê·¸
    0.23
    \xff
    0.23
    @stop
    0.22
    >//
    0.21
    BREAK
    0.21
     ';↵↵
    0.20
    =\"/
    0.20
    ]=-
    0.20
    Activations Density 0.001%

    No Known Activations