© 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. 4889
    Prev
    Next
    INDEX
    Explanations

    many things

    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
    Negative Logits
     mostly
    -0.08
     mainly
    -0.08
    _years
    -0.07
     courtesy
    -0.07
     considerable
    -0.07
    UB
    -0.07
     extra
    -0.07
    regunta
    -0.07
    argar
    -0.07
     repeatedly
    -0.06
    POSITIVE LOGITS
     Corey
    0.10
    Ñĥг
    0.10
    aket
    0.10
    alin
    0.09
     merits
    0.09
    acs
    0.09
     available
    0.09
    emp
    0.09
     Lynch
    0.09
    uiltin
    0.09
    Activations Density 0.224%

    No Known Activations