© 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. 55849
    Prev
    Next
    INDEX
    Explanations

    IT 000

    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
    ion
    -0.13
     Noon
    -0.10
    ic
    -0.10
    oom
    -0.10
    born
    -0.09
    hausen
    -0.09
    ine
    -0.09
     Century
    -0.09
     accent
    -0.09
    inal
    -0.08
    POSITIVE LOGITS
    efd
    0.09
    idges
    0.09
    peon
    0.09
    tam
    0.08
    UU
    0.08
     âĻ¥
    0.08
    erot
    0.08
     Knock
    0.07
    nock
    0.07
    otel
    0.07
    Activations Density 0.002%

    No Known Activations