© 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. 174
    Prev
    Next
    INDEX
    Explanations

    apart, without, alone

    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
     rin
    -0.08
    %);↵
    -0.08
    .catalog
    -0.08
    riel
    -0.07
    oss
    -0.07
    ë£
    -0.07
    owler
    -0.07
     Ess
    -0.07
    avi
    -0.07
    _inicio
    -0.07
    POSITIVE LOGITS
     without
    0.13
    without
    0.12
     alone
    0.11
     only
    0.11
     WITHOUT
    0.10
     rather
    0.10
     but
    0.09
    -independent
    0.09
     Wander
    0.09
     sans
    0.09
    Activations Density 3.910%

    No Known Activations