© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    HTML table attributes

    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
    ispens
    -0.26
    éħĬ
    -0.23
     èĩªåĬ¨çĶŁæĪIJ
    -0.23
    ONTAL
    -0.23
    DrawerToggle
    -0.22
     tph
    -0.21
    -Assad
    -0.21
    æĮŀ
    -0.21
    toDate
    -0.20
    >');
    -0.20
    POSITIVE LOGITS
    _firestore
    0.21
    ailer
    0.19
    æķ£åıij
    0.19
    å¹²åĺĽ
    0.19
     cellpadding
    0.19
     cellspacing
    0.19
    /frame
    0.19
    _MEMBERS
    0.19
    NavigationBar
    0.18
    纵
    0.18
    Activations Density 0.025%

    No Known Activations