© 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. 2685
    Prev
    Next
    INDEX
    Explanations

    article describes or summarizes

    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
     Hab
    -0.09
    irt
    -0.09
     slip
    -0.08
     suck
    -0.08
     dado
    -0.08
     Trap
    -0.08
    erness
    -0.08
    ìĦľ
    -0.08
     slips
    -0.08
     Hait
    -0.07
    POSITIVE LOGITS
    anine
    0.10
    ney
    0.10
    gang
    0.09
    imo
    0.09
     spinner
    0.09
    ród
    0.09
    xia
    0.09
     Forge
    0.09
    finger
    0.09
    ype
    0.09
    Activations Density 0.056%

    No Known Activations