© 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. 56456
    Prev
    Next
    INDEX
    Explanations

    André, Nav, Cin, Ang

    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
     Trotsky
    -0.09
    iele
    -0.08
    .dest
    -0.08
     Clown
    -0.08
     Tas
    -0.08
    algo
    -0.08
     Claw
    -0.08
    zew
    -0.08
    ammers
    -0.08
    seealso
    -0.08
    POSITIVE LOGITS
     Natural
    0.08
     happiest
    0.08
    pad
    0.08
    licative
    0.08
     Dann
    0.08
     consistent
    0.07
     spirit
    0.07
     Paper
    0.07
    ¥
    0.07
     precious
    0.07
    Activations Density 0.052%

    No Known Activations