© 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. 54785
    Prev
    Next
    INDEX
    Explanations

    files before . into and

    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
     procur
    -0.11
     Nichols
    -0.10
     needle
    -0.10
    urch
    -0.09
    jur
    -0.09
     Edu
    -0.09
     porn
    -0.09
    rapy
    -0.09
     GENERATED
    -0.09
     disarm
    -0.09
    POSITIVE LOGITS
     processes
    0.07
    van
    0.07
     AMS
    0.07
     recurs
    0.07
     mu
    0.07
     inv
    0.07
    .getRoot
    0.07
    flo
    0.07
    ICON
    0.06
    ]).
    0.06
    Activations Density 0.135%

    No Known Activations