© 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. 4114
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and sentence starters

    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
     then
    -0.10
    ensch
    -0.10
     Needless
    -0.09
     thereafter
    -0.09
    imd
    -0.09
    Then
    -0.09
     subsequently
    -0.09
    anse
    -0.09
     later
    -0.09
     Then
    -0.09
    POSITIVE LOGITS
    adel
    0.09
    ero
    0.09
    loo
    0.08
    alon
    0.08
    eras
    0.08
    umm
    0.08
    opr
    0.08
    ibo
    0.07
    065
    0.07
    lok
    0.07
    Activations Density 0.163%

    No Known Activations