© 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. 363
    Prev
    Next
    INDEX
    Explanations

    the

    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
    imity
    -0.24
    åĩ¤åĩ°ç½ij
    -0.23
    afone
    -0.22
    ();++
    -0.22
    *)_
    -0.22
    ombine
    -0.22
    á¼Ħ
    -0.21
    -Origin
    -0.21
    -scrollbar
    -0.21
    incy
    -0.21
    POSITIVE LOGITS
     most
    0.34
     equivalent
    0.30
     same
    0.29
     only
    0.29
    ologically
    0.27
     correct
    0.26
     envy
    0.25
     opposite
    0.25
    same
    0.24
     epit
    0.23
    Activations Density 2.431%

    No Known Activations