© 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. 56086
    Prev
    Next
    INDEX
    Explanations

    words indicating direction or relation

    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
    uto
    -0.09
    very
    -0.09
     carefully
    -0.09
     tender
    -0.09
    odo
    -0.09
    Wa
    -0.08
     everywhere
    -0.08
    ente
    -0.08
    ä¿
    -0.08
    911
    -0.08
    POSITIVE LOGITS
     Fog
    0.09
     possibly
    0.08
     potentially
    0.08
     considerations
    0.08
     Pot
    0.08
     notable
    0.08
    yms
    0.08
     noteworthy
    0.08
    borough
    0.07
     Possibly
    0.07
    Activations Density 0.119%

    No Known Activations