© 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. 994
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    effective
    -0.11
    -il
    -0.10
    -validate
    -0.10
    rete
    -0.10
    eligible
    -0.10
    wrapped
    -0.10
     incap
    -0.10
    guarded
    -0.09
    aida
    -0.09
    unch
    -0.09
    POSITIVE LOGITS
    ces
    0.12
    theless
    0.10
     necessarily
    0.09
    ethe
    0.09
    ograms
    0.08
    illion
    0.08
    ymous
    0.08
    acles
    0.08
    ame
    0.08
    ÑĩеÑĤ
    0.08
    Activations Density 0.651%

    No Known Activations