© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
     humour
    -0.12
     Whilst
    -0.11
     harbour
    -0.10
     Harbour
    -0.10
     flavour
    -0.10
     tyre
    -0.10
     firstly
    -0.10
     organisers
    -0.10
     defence
    -0.09
     flavours
    -0.09
    POSITIVE LOGITS
     Gallagher
    0.09
     RU
    0.09
    als
    0.09
     bingo
    0.09
     Suffolk
    0.09
    isbury
    0.09
     borough
    0.09
     SEND
    0.09
    acro
    0.09
     Borough
    0.09
    Activations Density 0.494%

    No Known Activations