© 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. 364
    Prev
    Next
    INDEX
    Explanations

    license header *

    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
    ând
    -0.08
    cy
    -0.08
    end
    -0.08
     Gret
    -0.08
     Rol
    -0.08
    ame
    -0.08
     wish
    -0.07
     solitary
    -0.07
    ingen
    -0.07
    ames
    -0.07
    POSITIVE LOGITS
    achu
    0.11
    -keys
    0.10
     valign
    0.10
    apid
    0.09
    ammo
    0.09
    uft
    0.09
     cellspacing
    0.09
    fone
    0.09
    -validate
    0.08
     ++)
    0.08
    Activations Density 1.051%

    No Known Activations