© 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. 53907
    Prev
    Next
    INDEX
    Explanations

    end of sentence or after punctuation

    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
     Griffin
    -0.10
    ãĥĬ
    -0.09
    nost
    -0.09
     graft
    -0.08
     nur
    -0.08
    dent
    -0.08
    itet
    -0.08
     jack
    -0.08
    ,{↵
    -0.08
    olor
    -0.08
    POSITIVE LOGITS
    din
    0.10
     ori
    0.09
     complains
    0.09
     obstruct
    0.08
    sp
    0.08
     stabil
    0.08
    DEX
    0.08
    sg
    0.08
    glob
    0.08
    nia
    0.08
    Activations Density 0.007%

    No Known Activations