© 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. 88
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
     komment
    -0.22
    NCY
    -0.21
    },č↵č↵
    -0.21
    ç§ģæľį
    -0.21
    ,},↵
    -0.20
    ðŁĺĬ
    -0.20
    czas
    -0.20
    为æĬĵ
    -0.20
    çıĪ
    -0.20
    _BUFF
    -0.20
    POSITIVE LOGITS
     retal
    0.20
    rowse
    0.20
     jihadist
    0.20
    ragments
    0.20
    inema
    0.19
     Playboy
    0.19
    voke
    0.19
    ä¸
    0.19
    ième
    0.18
    gence
    0.18
    Activations Density 0.002%

    No Known Activations