© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    information

    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
    >Password
    -0.23
    @dynamic
    -0.23
    á»ĥu
    -0.21
     ulus
    -0.21
    ]int
    -0.21
    _expiry
    -0.20
    );}↵↵
    -0.20
    oger
    -0.20
     gode
    -0.20
    .SwingConstants
    -0.20
    POSITIVE LOGITS
     hol
    0.21
    ÐĽÐŀ
    0.18
    ouch
    0.18
     dep
    0.17
     thrott
    0.17
    ifar
    0.17
    thic
    0.17
    aptors
    0.17
    ÐľÐŀ
    0.17
    .localtime
    0.17
    Activations Density 1.219%

    No Known Activations