© 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. 56955
    Prev
    Next
    INDEX
    Explanations

    !important declarations

    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
    eld
    -0.08
     yet
    -0.07
    folk
    -0.07
     coal
    -0.07
    pes
    -0.07
     little
    -0.07
     liber
    -0.07
    oil
    -0.07
     wisdom
    -0.07
     Coal
    -0.06
    POSITIVE LOGITS
    NS
    0.10
    uate
    0.09
     Schwe
    0.09
     Sachs
    0.09
     Replies
    0.09
    tempt
    0.09
    arbonate
    0.09
     bells
    0.09
     needed
    0.09
     Chop
    0.09
    Activations Density 0.001%

    No Known Activations