© 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. 54003
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    hek
    -0.11
    chants
    -0.10
    lix
    -0.10
    érc
    -0.10
    ervas
    -0.09
    egal
    -0.09
    ikal
    -0.09
    eci
    -0.09
     slack
    -0.09
     whirl
    -0.09
    POSITIVE LOGITS
    ugg
    0.09
     Vu
    0.09
    eras
    0.09
    rut
    0.08
     Cin
    0.08
    à¹Į
    0.08
     Marin
    0.08
     Other
    0.07
     Cer
    0.07
     other
    0.07
    Activations Density 0.004%

    No Known Activations