© 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. 915
    Prev
    Next
    INDEX
    Explanations

    code/special characters

    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
    owie
    -0.20
    æ¿Ģæĥħ
    -0.20
    Band
    -0.19
     BDSM
    -0.18
     Swinger
    -0.18
    yna
    -0.18
     anál
    -0.18
    entiful
    -0.18
    tparam
    -0.17
     rencont
    -0.17
    POSITIVE LOGITS
    -Identifier
    0.22
    /navbar
    0.21
     RoundedRectangle
    0.21
    âĿĵ
    0.20
    åī¯åİ¿éķ¿
    0.20
    åİ¿éķ¿
    0.20
    []}
    0.20
    íĨ
    0.20
    å¾Īå¤ļæľĭåıĭ
    0.19
    spiracy
    0.19
    Activations Density 0.001%

    No Known Activations