© 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. 2365
    Prev
    Next
    INDEX
    Explanations

    once again

    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
     spont
    -0.09
    esse
    -0.09
    oyo
    -0.09
    ESS
    -0.09
     Oral
    -0.09
    reck
    -0.09
    COPE
    -0.09
     neat
    -0.09
     sched
    -0.08
     oral
    -0.08
    POSITIVE LOGITS
    akis
    0.10
     Bowen
    0.08
     Smooth
    0.08
     Operation
    0.08
    rgb
    0.08
     marvel
    0.08
     annual
    0.08
     Wit
    0.08
    oven
    0.08
    urai
    0.08
    Activations Density 0.351%

    No Known Activations