© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    row manipulation

    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
    ual
    -0.08
    pike
    -0.08
    weg
    -0.08
    nal
    -0.08
    iam
    -0.08
    out
    -0.08
    amente
    -0.07
    bral
    -0.07
    àµįà´
    -0.07
    .NotNull
    -0.07
    POSITIVE LOGITS
    /column
    0.13
    bridge
    0.11
    dy
    0.11
    zee
    0.10
    etta
    0.10
    ULA
    0.10
    locks
    0.10
    inka
    0.10
    boat
    0.10
    fant
    0.09
    Activations Density 0.070%

    No Known Activations