© 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. 54089
    Prev
    Next
    INDEX
    Explanations

    Paul followed by a name

    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
    ently
    -0.09
    anut
    -0.09
    ly
    -0.09
    -0.08
    grounds
    -0.08
    chang
    -0.08
    olson
    -0.08
    imately
    -0.08
     xa
    -0.08
    haps
    -0.07
    POSITIVE LOGITS
    ings
    0.10
    ine
    0.09
     Presidency
    0.09
    ieber
    0.09
    inp
    0.09
    raj
    0.09
    inho
    0.09
    sen
    0.09
    outh
    0.08
     retrie
    0.08
    Activations Density 0.010%

    No Known Activations