© 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. 57482
    Prev
    Next
    INDEX
    Explanations

    institutional affiliations

    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
    ueue
    -0.10
     mus
    -0.08
    elsey
    -0.08
    pio
    -0.08
    fas
    -0.08
    ³³³
    -0.08
     obligatory
    -0.08
     Coupe
    -0.08
     Dest
    -0.08
     nic
    -0.08
    POSITIVE LOGITS
    aki
    0.09
     overst
    0.09
    standing
    0.08
    omi
    0.08
    shot
    0.08
    á
    0.08
    asha
    0.08
    Govern
    0.08
    usterity
    0.08
    abin
    0.08
    Activations Density 0.004%

    No Known Activations