© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    numbers and groups

    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
    _lists
    -0.11
     Lists
    -0.10
     thousands
    -0.09
    Lists
    -0.09
    abet
    -0.09
    oco
    -0.09
     everywhere
    -0.09
    rich
    -0.09
    >[]
    -0.09
    actor
    -0.08
    POSITIVE LOGITS
     collectively
    0.21
     three
    0.17
     four
    0.16
     totaling
    0.16
    (each
    0.16
     individually
    0.16
     each
    0.16
    each
    0.16
    éĥ½
    0.15
    (all
    0.14
    Activations Density 3.610%

    No Known Activations