© 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. 3706
    Prev
    Next
    INDEX
    Explanations

    healing scar

    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
    	INNER
    -0.23
    .minute
    -0.22
    noinspection
    -0.21
    inati
    -0.20
    ToMany
    -0.18
    esModule
    -0.18
    åIJŁ
    -0.18
    仪
    -0.18
     yOffset
    -0.18
    twig
    -0.17
    POSITIVE LOGITS
    éĩį建
    0.32
     healing
    0.27
    ä¿®å¤į
    0.27
    çĻį
    0.25
    Scar
    0.23
     scar
    0.22
    scar
    0.22
     Healing
    0.22
     Heal
    0.21
    çĨ¬
    0.21
    Activations Density 0.887%

    No Known Activations