© 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. 57799
    Prev
    Next
    INDEX
    Explanations

    arrangement, ownership, policy, material, cavity, haircut, scheme, environment

    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
     behold
    -0.10
     confidently
    -0.08
    ,*
    -0.08
    ãĥ©
    -0.08
     Chow
    -0.08
    elles
    -0.08
     contiguous
    -0.08
    aines
    -0.08
     whom
    -0.08
    hand
    -0.08
    POSITIVE LOGITS
    entes
    0.09
    ristol
    0.08
     ;↵
    0.08
    IBC
    0.08
     transplant
    0.08
    kke
    0.08
    ';
    0.08
    fore
    0.08
    seo
    0.08
    forest
    0.08
    Activations Density 0.053%

    No Known Activations