© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    title

    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
     '-';↵
    -0.25
     Dich
    -0.22
     }?>↵
    -0.21
    伪
    -0.21
     *</
    -0.19
     bénéfic
    -0.19
    erÃŃa
    -0.19
     lehet
    -0.19
    loy
    -0.19
    줬
    -0.18
    POSITIVE LOGITS
    OnInit
    0.23
    иÑĤелÑĮн
    0.22
    çĨ¨
    0.21
    oliday
    0.21
    celand
    0.21
    iators
    0.20
     :";↵
    0.19
    'field
    0.19
    redient
    0.19
    .ObjectMeta
    0.19
    Activations Density 0.017%

    No Known Activations