© 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. 55201
    Prev
    Next
    INDEX
    Explanations

    rs numbers

    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
    oot
    -0.10
     theirs
    -0.09
     rouge
    -0.09
    uss
    -0.09
    eti
    -0.09
    —from
    -0.08
     crud
    -0.08
     bunny
    -0.08
    kon
    -0.08
     hindsight
    -0.08
    POSITIVE LOGITS
     ENT
    0.09
     Compensation
    0.09
     aos
    0.08
    extr
    0.08
    whole
    0.08
    EEK
    0.08
    KN
    0.08
    /topics
    0.08
    /Application
    0.07
    leave
    0.07
    Activations Density 0.015%

    No Known Activations