© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    is

    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
     undefeated
    -0.10
     %-
    -0.09
     wg
    -0.09
     conventional
    -0.09
     vy
    -0.09
    Lit
    -0.09
    ruz
    -0.08
    pper
    -0.08
    trap
    -0.08
     untreated
    -0.08
    POSITIVE LOGITS
     ever
    0.12
     EVER
    0.10
    aber
    0.09
     Ever
    0.09
    atel
    0.09
     anything
    0.09
     cooper
    0.08
    Ever
    0.08
    iar
    0.08
     imaginable
    0.08
    Activations Density 0.117%

    No Known Activations