© 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. 57897
    Prev
    Next
    INDEX
    Explanations

    options assignment

    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
     Bis
    -0.09
    ideo
    -0.09
    ith
    -0.08
     bis
    -0.08
     crafts
    -0.08
     em
    -0.08
    agnost
    -0.08
    NAL
    -0.07
     offending
    -0.07
     masc
    -0.07
    POSITIVE LOGITS
    tail
    0.10
     Remix
    0.09
    her
    0.09
     Merchant
    0.09
     getConfig
    0.09
    SearchParams
    0.09
     tail
    0.09
     getopt
    0.09
     Dod
    0.09
     Saved
    0.09
    Activations Density 0.073%

    No Known Activations