© 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. 2708
    Prev
    Next
    INDEX
    Explanations

    odds ratios and risks

    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
     Aim
    -0.08
     measurements
    -0.08
    elden
    -0.08
     Measurements
    -0.08
     properties
    -0.08
     distributions
    -0.08
     polar
    -0.07
     phase
    -0.07
     figures
    -0.07
     recreate
    -0.07
    POSITIVE LOGITS
     odds
    0.13
     Odds
    0.11
     Positioned
    0.10
     actionable
    0.10
    odu
    0.10
     fold
    0.10
     Fey
    0.10
    opp
    0.10
     conditional
    0.10
     Conditional
    0.09
    Activations Density 0.272%

    No Known Activations