© 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. 61160
    Prev
    Next
    INDEX
    Explanations

    publication rule prohibits

    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
     amnesty
    -0.09
    nat
    -0.08
    amar
    -0.08
    jes
    -0.07
     ferry
    -0.07
    reuse
    -0.07
    viz
    -0.07
     visit
    -0.07
    kor
    -0.07
     ramp
    -0.07
    POSITIVE LOGITS
     Latter
    0.10
     fore
    0.10
     "../../../
    0.09
    Slash
    0.09
    еÑģÑĤв
    0.09
    zt
    0.09
     Cata
    0.09
     Sadd
    0.09
    istrator
    0.09
    acic
    0.09
    Activations Density 0.005%

    No Known Activations