© 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. 54850
    Prev
    Next
    INDEX
    Explanations

    comments off

    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
    trib
    -0.10
     Lorem
    -0.10
    ixo
    -0.09
    atz
    -0.09
    pak
    -0.09
    bil
    -0.09
    isti
    -0.09
    غ
    -0.08
     catching
    -0.08
     passing
    -0.08
    POSITIVE LOGITS
    ingen
    0.09
     Horm
    0.09
     surplus
    0.08
     hormone
    0.08
    quent
    0.08
     Via
    0.07
     cur
    0.07
     Say
    0.07
    ев
    0.07
     greeted
    0.07
    Activations Density 0.009%

    No Known Activations