© 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. 4697
    Prev
    Next
    INDEX
    Explanations

    field k

    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
     Cov
    -0.09
    inch
    -0.08
    esto
    -0.08
     eating
    -0.08
    cla
    -0.08
     office
    -0.08
     appell
    -0.07
    amen
    -0.07
    endon
    -0.07
     eat
    -0.07
    POSITIVE LOGITS
     Mobil
    0.10
     collaps
    0.10
    oil
    0.10
    ocate
    0.09
     barric
    0.09
    ihat
    0.09
     Wheels
    0.09
     Lakes
    0.09
     Lub
    0.09
    zew
    0.09
    Activations Density 0.061%

    No Known Activations