© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    time and specific labels

    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
     RequestMethod
    -0.23
     POLITICO
    -0.22
     démarch
    -0.20
    olicitud
    -0.20
     PartialView
    -0.20
    èħł
    -0.19
     (~(
    -0.19
    /GPL
    -0.19
    ç½Ķ
    -0.19
    ups
    -0.18
    POSITIVE LOGITS
    =edge
    0.21
    égorie
    0.21
    vit
    0.20
    SCO
    0.20
    incinn
    0.19
    aramel
    0.19
    éparation
    0.19
     bada
    0.19
    hape
    0.19
    agit
    0.19
    Activations Density 0.001%

    No Known Activations