© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3873
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åľ®
    -0.23
    «
    -0.22
    øj
    -0.21
    .touches
    -0.21
     alertController
    -0.21
     form
    -0.19
     certain
    -0.19
     being
    -0.19
    \Queue
    -0.19
     PureComponent
    -0.19
    POSITIVE LOGITS
    (strpos
    0.27
     miglior
    0.26
    )↵↵↵↵↵↵↵↵
    0.24
    !!");↵
    0.22
    ereotype
    0.22
    'R
    0.22
    anuts
    0.21
    -divider
    0.21
    xies
    0.21
    _HERSHEY
    0.21
    Activations Density 0.000%

    No Known Activations