© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55724
    Prev
    Next
    INDEX
    Explanations

    as the

    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
    oti
    -0.10
    ffi
    -0.09
    á»ijng
    -0.09
     downs
    -0.09
    elf
    -0.09
    eness
    -0.09
    iese
    -0.09
    .TryParse
    -0.09
     drag
    -0.08
     Mein
    -0.08
    POSITIVE LOGITS
    ulle
    0.12
    wil
    0.09
    iare
    0.08
     outset
    0.08
     crow
    0.08
     wil
    0.08
     saying
    0.08
    clare
    0.07
     foregoing
    0.07
     embodiment
    0.07
    Activations Density 0.028%

    No Known Activations