© 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. 4945
    Prev
    Next
    INDEX
    Explanations

    free and unrestricted options

    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
    Published
    -0.08
    æĺİ
    -0.08
    CreateDate
    -0.08
     unexpectedly
    -0.07
     surprisingly
    -0.07
     unnecessarily
    -0.07
    verty
    -0.07
    BOOL
    -0.07
     Kunst
    -0.07
    essler
    -0.07
    POSITIVE LOGITS
     freely
    0.21
     freedom
    0.14
     unrestricted
    0.13
     experimentation
    0.12
     Freed
    0.12
     libre
    0.11
     experimenting
    0.11
    fre
    0.11
    /free
    0.11
     impunity
    0.11
    Activations Density 0.274%

    No Known Activations