© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    hypothesize, theorize, findings, research

    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
    hee
    -0.09
     retrospect
    -0.09
    feas
    -0.08
    riteria
    -0.08
    /Product
    -0.08
     patent
    -0.08
    opyright
    -0.08
    loff
    -0.08
     nomin
    -0.08
     Niet
    -0.08
    POSITIVE LOGITS
     hypo
    0.12
     pars
    0.11
     Hyp
    0.08
     lub
    0.08
     psychologists
    0.08
     cleanly
    0.08
    anel
    0.08
    "She
    0.08
     theor
    0.08
     theorists
    0.08
    Activations Density 0.280%

    No Known Activations