© 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. 57935
    Prev
    Next
    INDEX
    Explanations

    world-wide-web, wide information

    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
    nio
    -0.10
     grounded
    -0.09
     cab
    -0.09
    jump
    -0.09
    unset
    -0.08
    aria
    -0.08
    ornings
    -0.08
    acom
    -0.08
    sip
    -0.08
    aram
    -0.08
    POSITIVE LOGITS
    vak
    0.10
     poil
    0.08
     Marr
    0.08
     fitted
    0.08
     boo
    0.07
     Nak
    0.07
    iki
    0.07
     converged
    0.07
    .EventQueue
    0.07
    iana
    0.07
    Activations Density 0.004%

    No Known Activations