© 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. 58182
    Prev
    Next
    INDEX
    Explanations

    opportunity, rationale, need

    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
     Pane
    -0.09
    ÂĢÂĻ
    -0.09
    ,[],
    -0.08
    apyrus
    -0.08
    hread
    -0.08
    sw
    -0.08
    tra
    -0.08
     bookings
    -0.08
     ensuing
    -0.08
    /am
    -0.07
    POSITIVE LOGITS
     backs
    0.10
     Cong
    0.08
     backed
    0.08
     simple
    0.08
     Cooperative
    0.08
     chief
    0.08
    etti
    0.08
     zipper
    0.08
     hom
    0.08
    è´
    0.08
    Activations Density 0.043%

    No Known Activations