© 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. 54392
    Prev
    Next
    INDEX
    Explanations

    major/leading cause

    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
    ampo
    -0.10
    -ok
    -0.10
     bols
    -0.09
    bine
    -0.09
    ihn
    -0.09
     Gest
    -0.09
    otto
    -0.09
    suming
    -0.09
    oundation
    -0.09
    -basic
    -0.09
    POSITIVE LOGITS
     rele
    0.10
    ADI
    0.08
     opinion
    0.08
     solic
    0.07
     Barr
    0.07
     cause
    0.07
     Opinion
    0.07
     Caf
    0.07
     issuing
    0.07
    resh
    0.07
    Activations Density 0.049%

    No Known Activations