© 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. 2989
    Prev
    Next
    INDEX
    Explanations

    exposure activities

    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
    RouterModule
    -0.23
    uguay
    -0.23
    uccess
    -0.22
     Erectile
    -0.21
     AUTHORS
    -0.21
    ebin
    -0.20
    omination
    -0.20
    ServletRequest
    -0.20
    ulfilled
    -0.20
    OLLOW
    -0.19
    POSITIVE LOGITS
    ä¸įå½ĵ
    0.28
     activities
    0.28
    ä¸įç»ıæĦı
    0.25
    æݥ触åĪ°
    0.25
    æļ´éľ²
    0.25
     exposures
    0.23
     exposure
    0.23
    使çĶ¨çļĦ
    0.23
     unprotected
    0.23
    Activities
    0.22
    Activations Density 1.285%

    No Known Activations