© 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. 55235
    Prev
    Next
    INDEX
    Explanations

    Friday night

    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
    ful
    -0.12
    ively
    -0.11
    ingly
    -0.11
    fully
    -0.10
     Aff
    -0.10
    aff
    -0.10
    erc
    -0.10
    ing
    -0.10
    ive
    -0.09
    iveness
    -0.09
    POSITIVE LOGITS
    ity
    0.10
    isz
    0.09
    keit
    0.09
    ÑĤе
    0.09
    aj
    0.09
    opoulos
    0.09
    hir
    0.08
    osh
    0.08
    ohl
    0.08
    ESH
    0.08
    Activations Density 0.009%

    No Known Activations