© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    previous

    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
     successors
    -0.19
     afterward
    -0.19
    #+
    -0.19
    éĴ«
    -0.19
     pam
    -0.18
    -labelledby
    -0.18
    -pills
    -0.18
    çݹ
    -0.18
    eterangan
    -0.18
    unga
    -0.18
    POSITIVE LOGITS
     earlier
    0.35
     previous
    0.34
     Earlier
    0.32
     Previous
    0.30
    previous
    0.29
    ä¹ĭåīįçļĦ
    0.28
    Previous
    0.28
    Earlier
    0.28
     prior
    0.26
     lesser
    0.26
    Activations Density 0.618%

    No Known Activations