© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    General context

    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
     Hannity
    -0.23
     fkk
    -0.21
    ë´ħ
    -0.21
    inding
    -0.20
     stoi
    -0.20
    éļĶ
    -0.19
     MediaTek
    -0.19
    FFECT
    -0.19
     RoundedRectangle
    -0.19
    è¶Ĭ
    -0.19
    POSITIVE LOGITS
    nü
    0.24
    keterangan
    0.22
    nte
    0.20
    quisites
    0.20
    enerima
    0.20
     there
    0.20
    ]={↵
    0.20
    idges
    0.19
    flate
    0.19
    aternity
    0.19
    Activations Density 0.002%

    No Known Activations