© 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. 53984
    Prev
    Next
    INDEX
    Explanations

    shape and width measurements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Madd
    -0.10
     ?>↵↵↵
    -0.10
     Gul
    -0.09
    argo
    -0.09
    yo
    -0.09
    agon
    -0.09
     substr
    -0.09
    ieg
    -0.09
    ico
    -0.08
     Hos
    -0.08
    POSITIVE LOGITS
    cont
    0.09
     sme
    0.08
     skirt
    0.08
    Trait
    0.08
    _trait
    0.08
     wings
    0.08
     trait
    0.08
     sm
    0.08
    -cont
    0.08
     cont
    0.08
    Activations Density 0.028%

    No Known Activations