© 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. 8624
    Prev
    Next
    INDEX
    Explanations

    Go Authors copyright

    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
    ed
    -0.09
     into
    -0.09
    ages
    -0.09
    ing
    -0.09
     sqr
    -0.08
     Kahn
    -0.08
    issy
    -0.08
    ssue
    -0.08
    adan
    -0.08
     offs
    -0.08
    POSITIVE LOGITS
    0.09
    nal
    0.09
    PMC
    0.09
    aven
    0.08
     eg
    0.08
    itate
    0.08
    xxxx
    0.08
     punct
    0.08
    ize
    0.08
     ing
    0.08
    Activations Density 0.055%

    No Known Activations