© 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. 56458
    Prev
    Next
    INDEX
    Explanations

    US states

    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
     universally
    -0.09
     pip
    -0.08
     Brewer
    -0.08
     association
    -0.07
     univers
    -0.07
     Rand
    -0.07
    ve
    -0.07
    eworthy
    -0.07
    ment
    -0.07
     Moy
    -0.07
    POSITIVE LOGITS
    uder
    0.11
    ayah
    0.10
    itar
    0.10
    FTER
    0.09
     üzer
    0.09
    arias
    0.09
    olare
    0.09
    rieg
    0.09
    roman
    0.09
    ANTED
    0.09
    Activations Density 0.036%

    No Known Activations