© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4247
    Prev
    Next
    INDEX
    Explanations

    contrast, exception, alternative

    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
    opo
    -0.09
    AO
    -0.09
     seedu
    -0.08
    bourg
    -0.08
    forme
    -0.08
    .pt
    -0.08
     lite
    -0.08
    Å¡t
    -0.07
    itti
    -0.07
     DIAG
    -0.07
    POSITIVE LOGITS
     instead
    0.12
     unlike
    0.11
     &(
    0.10
    Unlike
    0.09
     Unlike
    0.09
    instead
    0.09
     Wer
    0.09
     Instead
    0.09
     Nev
    0.09
     rather
    0.09
    Activations Density 0.242%

    No Known Activations