© 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. 53726
    Prev
    Next
    INDEX
    Explanations

    corner 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
    ynet
    -0.09
     Alive
    -0.09
     overst
    -0.08
     Stam
    -0.08
     Bett
    -0.08
    ney
    -0.08
    leta
    -0.08
     Voll
    -0.08
    iya
    -0.08
     rede
    -0.08
    POSITIVE LOGITS
     corner
    0.18
    corner
    0.17
    Corner
    0.14
    -corner
    0.13
     Corner
    0.13
     corners
    0.12
    è§Ĵ
    0.11
    ëŀĺ
    0.10
     quadrant
    0.10
    erd
    0.10
    Activations Density 0.009%

    No Known Activations