© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    variable names followed by assignment

    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
     bare
    -0.08
    ilarity
    -0.07
     Bare
    -0.07
    iate
    -0.07
     trif
    -0.07
    Metro
    -0.07
     rough
    -0.07
     reinterpret
    -0.06
    doi
    -0.06
    zz
    -0.06
    POSITIVE LOGITS
    uD
    0.11
    spe
    0.11
    antry
    0.10
     worse
    0.10
    aders
    0.10
    portun
    0.10
    amu
    0.10
    dfd
    0.10
    sla
    0.10
    âĶĢâĶĢ
    0.10
    Activations Density 0.223%

    No Known Activations