© 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. 2318
    Prev
    Next
    INDEX
    Explanations

    step, criteria, omission, B

    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
    reh
    -0.12
    nyder
    -0.10
    ymi
    -0.10
     pars
    -0.09
     grues
    -0.09
     smooth
    -0.09
    entiful
    -0.09
     unfold
    -0.09
     kickoff
    -0.09
     uncomp
    -0.09
    POSITIVE LOGITS
     omitted
    0.10
    mine
    0.09
     instead
    0.08
     omission
    0.08
     because
    0.08
    225
    0.08
     incorrectly
    0.08
     strangely
    0.08
    oin
    0.08
    zej
    0.08
    Activations Density 0.399%

    No Known Activations