© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 80
    Prev
    Next
    INDEX
    Explanations

    tech terms

    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
     èĩªåĬ¨çĶŁæĪIJ
    -0.35
    âļĹ
    -0.35
     Ủ
    -0.33
    byss
    -0.33
     WIFI
    -0.31
    ï¼Ħ
    -0.31
    ðŁĵIJ
    -0.30
    zzle
    -0.29
    (___
    -0.29
    (Have
    -0.29
    POSITIVE LOGITS
     dumpsters
    0.37
     maduras
    0.35
     ApiException
    0.30
     unmist
    0.30
     vej
    0.29
     sophistic
    0.29
    Slf
    0.28
     Millenn
    0.28
     Interracial
    0.28
     ál
    0.28
    Activations Density 9.902%

    No Known Activations