© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    knownMethod 1: MAX_ACTIVATING_TOKENS are all the same token.known

    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
    ä¼¥
    -0.23
     mù
    -0.23
    vore
    -0.23
    :'.$
    -0.21
    sonian
    -0.21
    ntl
    -0.21
    @student
    -0.21
    çĸ¡
    -0.21
    obierno
    -0.21
     Leban
    -0.21
    POSITIVE LOGITS
     Known
    0.25
    *>*
    0.23
    äºĭ實
    0.20
     skype
    0.19
    обÑīа
    0.19
    برج
    0.18
     '%"
    0.18
    known
    0.18
    .getInputStream
    0.18
    Known
    0.18
    Activations Density 0.095%

    No Known Activations