© 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. 4196
    Prev
    Next
    INDEX
    Explanations

    cytokines

    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
    wing
    -0.09
    aad
    -0.08
    enco
    -0.08
    ìĥī
    -0.08
    aidu
    -0.08
     Cliff
    -0.08
    resden
    -0.08
    ixon
    -0.08
    eden
    -0.08
    foo
    -0.08
    POSITIVE LOGITS
    inesis
    0.11
    ãĥ«
    0.10
    ings
    0.09
    ines
    0.09
     pin
    0.09
    IKE
    0.09
     exchanged
    0.09
    inin
    0.08
    Tok
    0.08
    raph
    0.08
    Activations Density 0.024%

    No Known Activations