© 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. 54142
    Prev
    Next
    INDEX
    Explanations

    `/share` paths

    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
     chute
    -0.11
     Seas
    -0.10
     SHARES
    -0.10
    -running
    -0.10
     seas
    -0.09
     Corm
    -0.09
     Lair
    -0.09
    aza
    -0.09
     Curtain
    -0.09
    jom
    -0.09
    POSITIVE LOGITS
     pe
    0.08
    ty
    0.08
    agar
    0.07
    asc
    0.07
    AMI
    0.07
     PC
    0.07
    pent
    0.07
    holder
    0.07
    gd
    0.07
    struct
    0.07
    Activations Density 0.002%

    No Known Activations