© 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. 55191
    Prev
    Next
    INDEX
    Explanations

    .mock, import, module

    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
     deflect
    -0.09
     fed
    -0.08
    SOC
    -0.08
     Bell
    -0.08
    ĺ
    -0.08
     ingr
    -0.08
     neglected
    -0.07
    aman
    -0.07
     slew
    -0.07
     Forget
    -0.07
    POSITIVE LOGITS
    Annotations
    0.15
    .when
    0.13
    .mock
    0.10
    .verify
    0.09
    .times
    0.09
    phy
    0.09
     Inline
    0.08
    ndo
    0.08
    eln
    0.08
     jam
    0.08
    Activations Density 0.002%

    No Known Activations