© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    measured quantities

    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
     "{\"
    -0.23
    室åıĭ
    -0.23
    åħį
    -0.22
    çĪ¶
    -0.21
    æľĢå¤ļ
    -0.21
    åĪĩ
    -0.21
    åħ±
    -0.20
    ttl
    -0.19
     cornerback
    -0.19
    Ï´
    -0.19
    POSITIVE LOGITS
    åĢ¼
    0.33
     embod
    0.28
    .za
    0.27
    ;o
    0.26
    owntown
    0.24
    OMPI
    0.24
    æ°´å¹³
    0.24
     levels
    0.24
    esub
    0.23
     !***
    0.23
    Activations Density 3.099%

    No Known Activations