© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1164
    Prev
    Next
    INDEX
    Explanations

    .

    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
     Erotic
    -0.36
     Interracial
    -0.32
     Erectile
    -0.27
     Tatto
    -0.27
     Prostit
    -0.27
     Parenthood
    -0.26
    kontakte
    -0.24
     Emblem
    -0.23
    Hôtel
    -0.23
     Wrest
    -0.23
    POSITIVE LOGITS
     It
    0.31
     The
    0.30
    çī¹çĤ¹æĺ¯
    0.30
     it
    0.28
     during
    0.27
    çĶ±äºİ
    0.26
     They
    0.26
     each
    0.26
     During
    0.26
     initially
    0.25
    Activations Density 4.330%

    No Known Activations