© 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. 58598
    Prev
    Next
    INDEX
    Explanations

    here

    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
     Meer
    -0.09
     Derek
    -0.08
    éal
    -0.08
    sal
    -0.08
    ntag
    -0.08
    ĵį
    -0.08
     Basis
    -0.08
     découvrir
    -0.08
    ½Ķ
    -0.08
     Representatives
    -0.08
    POSITIVE LOGITS
    verted
    0.09
    packed
    0.09
    uin
    0.09
    onda
    0.09
    uras
    0.08
    onne
    0.08
     Velvet
    0.08
    :false
    0.08
    ewise
    0.08
     Ñģам
    0.08
    Activations Density 0.015%

    No Known Activations