© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61866
    Prev
    Next
    INDEX
    Explanations

    spellings and spelling out

    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
    Negative Logits
    ruk
    -0.10
     Alam
    -0.10
    keit
    -0.10
    erule
    -0.10
    esan
    -0.10
    Patch
    -0.09
    еÑģÑĤво
    -0.09
    mdl
    -0.09
    han
    -0.09
     Caul
    -0.09
    POSITIVE LOGITS
    bind
    0.11
    oyer
    0.09
    ings
    0.09
    ont
    0.08
     Hav
    0.08
    etch
    0.08
    ly
    0.08
    Ñĭв
    0.08
    ships
    0.08
    borg
    0.07
    Activations Density 0.003%

    No Known Activations