© 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. 4468
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
    elic
    -0.09
    zar
    -0.09
     awards
    -0.09
    å¼Ĥ常
    -0.09
     unlike
    -0.09
     totally
    -0.08
     winners
    -0.08
     award
    -0.08
    alf
    -0.08
    kus
    -0.08
    POSITIVE LOGITS
    azz
    0.09
     od
    0.08
     restraining
    0.08
    onga
    0.07
    ock
    0.07
     programas
    0.07
    essa
    0.07
    ardi
    0.07
     behind
    0.07
    led
    0.07
    Activations Density 0.140%

    No Known Activations