© 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. 3333
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    ibrator
    -0.24
    ennifer
    -0.24
    NullOr
    -0.23
    foundland
    -0.23
    å«ī
    -0.21
    );$
    -0.20
    opleft
    -0.20
    ediator
    -0.20
    _Api
    -0.20
     $_[
    -0.20
    POSITIVE LOGITS
     minden
    0.22
     goo
    0.21
    .Texture
    0.19
    éĢĥ
    0.19
     csak
    0.18
    å¿Ĩ
    0.18
     wake
    0.18
    eldo
    0.18
    CRET
    0.17
    æ®ļ
    0.17
    Activations Density 0.001%

    No Known Activations