© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57900
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
     ?:
    -0.10
     carp
    -0.09
    arp
    -0.08
    imi
    -0.08
     kettle
    -0.08
     cons
    -0.08
    orts
    -0.08
    Lit
    -0.08
    ERY
    -0.08
     quis
    -0.08
    POSITIVE LOGITS
    ooth
    0.10
    áºŃt
    0.09
    ene
    0.08
    aign
    0.08
    pper
    0.08
     Ke
    0.08
     somewhere
    0.08
     Abd
    0.08
     showing
    0.08
     Cohen
    0.08
    Activations Density 0.014%

    No Known Activations