© 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. 55157
    Prev
    Next
    INDEX
    Explanations

    omega-3 fatty acids, metabolites, scientific terms

    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
    worth
    -0.11
    led
    -0.11
    oS
    -0.11
    elda
    -0.11
    ting
    -0.10
    TING
    -0.10
    o
    -0.09
    abella
    -0.09
    ewing
    -0.09
    fish
    -0.09
    POSITIVE LOGITS
    å½ķ
    0.09
    inst
    0.08
    ics
    0.08
     Span
    0.08
    din
    0.08
    istic
    0.08
    ģ
    0.07
    ist
    0.07
    entic
    0.07
    antis
    0.07
    Activations Density 0.003%

    No Known Activations