© 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. 2643
    Prev
    Next
    INDEX
    Explanations

    say "1"

    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
    å¹´ä¹ĭä¹ħ
    -0.25
    indr
    -0.20
    peater
    -0.19
    ácil
    -0.19
    modifiable
    -0.18
    resses
    -0.18
    çĶ°
    -0.18
    bsites
    -0.18
    éŃij
    -0.18
     gutter
    -0.17
    POSITIVE LOGITS
    'icon
    0.29
    /MIT
    0.29
    'options
    0.27
    âľį
    0.24
    /Instruction
    0.24
    /↵↵↵↵
    0.24
    'url
    0.23
    设计åĻ¨
    0.22
    /Branch
    0.22
    -deals
    0.22
    Activations Density 0.428%

    No Known Activations