© 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. 8585
    Prev
    Next
    INDEX
    Explanations

    words ending in common suffixes

    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
    e
    -0.15
    imensional
    -0.14
    o
    -0.14
    er
    -0.13
    egative
    -0.13
    scious
    -0.13
    riendly
    -0.13
    etwork
    -0.13
    riting
    -0.12
    uman
    -0.12
    POSITIVE LOGITS
    istra
    0.10
    canf
    0.10
    vironment
    0.09
    amples
    0.09
    еÑģÑĤи
    0.08
    ello
    0.08
    ambda
    0.08
    onus
    0.08
    blem
    0.08
    lug
    0.08
    Activations Density 0.218%

    No Known Activations