© 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. 465
    Prev
    Next
    INDEX
    Explanations

    direction or side

    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
    åıĬ缸åħ³
    -0.23
    åĨħå¤ĸ
    -0.22
    çħ
    -0.20
    rikes
    -0.20
    amedi
    -0.19
     Blasio
    -0.19
    /navbar
    -0.19
    大大å°ı
    -0.19
    presso
    -0.19
    awks
    -0.19
    POSITIVE LOGITS
    -side
    0.37
    -only
    0.30
     side
    0.30
    -facing
    0.29
    쪽
    0.28
    side
    0.28
    ward
    0.27
    -leaning
    0.27
    åģ´
    0.26
    侧
    0.25
    Activations Density 4.845%

    No Known Activations