© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    old fashioned expressions

    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
    ANC
    -0.10
    isti
    -0.09
    uchar
    -0.09
     jer
    -0.09
    asp
    -0.09
    [sizeof
    -0.08
    uttgart
    -0.08
    andon
    -0.08
    -access
    -0.08
    isoner
    -0.08
    POSITIVE LOGITS
     hefty
    0.12
     handy
    0.10
    uss
    0.09
     conj
    0.09
     chunk
    0.09
     nip
    0.09
     pals
    0.08
     mighty
    0.08
     folks
    0.08
     Mr
    0.08
    Activations Density 0.550%

    No Known Activations