© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    positive

    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
     createState
    -0.25
    itrust
    -0.23
    .AdapterView
    -0.23
    byss
    -0.22
    izontally
    -0.22
    ansom
    -0.22
    NavController
    -0.22
    ancellable
    -0.21
    rysler
    -0.21
    presso
    -0.21
    POSITIVE LOGITS
    -positive
    0.23
    ahrain
    0.23
     Positive
    0.21
    -negative
    0.21
    .FileReader
    0.20
     associations
    0.20
     altercation
    0.20
    ê°¯
    0.20
    -thinking
    0.19
     association
    0.19
    Activations Density 0.084%

    No Known Activations