© 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. 3687
    Prev
    Next
    INDEX
    Explanations

    world

    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
    HEIGHT
    -0.25
    __;
    -0.25
     ucwords
    -0.25
    üyü
    -0.24
    STRU
    -0.22
    å©ķ
    -0.21
    婧
    -0.21
    ucson
    -0.21
    @update
    -0.21
     überh
    -0.20
    POSITIVE LOGITS
    liness
    0.31
    èĮĥåĽ´åĨħ
    0.24
    views
    0.24
    theless
    0.23
    ifestyles
    0.22
    /local
    0.21
    Wide
    0.21
    绿åŁİ
    0.21
    ratulations
    0.21
     décid
    0.20
    Activations Density 0.163%

    No Known Activations