© 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. 968
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    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
    Ø£ÙĪض
    -0.35
    -basket
    -0.33
    å°±ç»Ļ大家
    -0.30
     èĭ¥è¦ģ
    -0.30
    ",__
    -0.30
    ----</
    -0.29
    åħ¨èµĦåŃIJ
    -0.29
    @dynamic
    -0.29
     safeg
    -0.28
     indeb
    -0.28
    POSITIVE LOGITS
    -
    0.45
    ·
    0.26
    -↵
    0.26
    -up
    0.25
    -ever
    0.25
    -than
    0.24
    -h
    0.24
    -(
    0.23
    -out
    0.23
    -c
    0.22
    Activations Density 3.829%

    No Known Activations