© 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. 61567
    Prev
    Next
    INDEX
    Explanations

    apart aside notwithstanding

    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
    icol
    -0.09
    .getElementsByName
    -0.08
    aims
    -0.08
     Hope
    -0.08
     onSuccess
    -0.08
    pekt
    -0.08
    trail
    -0.08
     tamp
    -0.08
     dispos
    -0.08
    icing
    -0.08
    POSITIVE LOGITS
     aside
    0.22
     notwithstanding
    0.21
     Aside
    0.14
     apart
    0.13
    aside
    0.12
     Apart
    0.10
     permitting
    0.10
     erased
    0.09
    withstanding
    0.09
    Apart
    0.08
    Activations Density 0.165%

    No Known Activations