© 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. 1525
    Prev
    Next
    INDEX
    Explanations

    B

    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
    تظ
    -0.36
    RITE
    -0.31
    еÑģÑĤеÑģÑĤв
    -0.29
    OUNCE
    -0.27
    سبÙĪع
    -0.27
    IFEST
    -0.25
    OOT
    -0.24
    ÙģØ°
    -0.24
     bénéficie
    -0.24
    iaÅĤa
    -0.23
    POSITIVE LOGITS
    ungalow
    0.42
    rescia
    0.35
    ishops
    0.34
    autiful
    0.30
    agini
    0.30
    ologna
    0.29
    escort
    0.28
    ispens
    0.27
    adiator
    0.27
    hazi
    0.27
    Activations Density 4.133%

    No Known Activations