© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55655
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compared
    -0.23
     Compared
    -0.21
     unlike
    -0.15
     differs
    -0.13
    Unlike
    -0.12
     Unlike
    -0.12
     Compare
    -0.12
     differed
    -0.12
    richt
    -0.12
     compare
    -0.12
    POSITIVE LOGITS
    aul
    0.10
     entirely
    0.08
    oul
    0.08
    noise
    0.08
     similar
    0.07
     similarly
    0.07
    olum
    0.07
    æĬ
    0.07
     departments
    0.07
    æ¼
    0.07
    Activations Density 0.061%

    No Known Activations