© 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. 620
    Prev
    Next
    INDEX
    Explanations

    is followed by a state or quality

    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
    -0.10
     its
    -0.09
     preferably
    -0.08
     eup
    -0.08
     itself
    -0.08
    _it
    -0.08
     present
    -0.07
    its
    -0.07
     it
    -0.07
    rf
    -0.07
    POSITIVE LOGITS
     raining
    0.23
     incumbent
    0.18
     possible
    0.17
     impossible
    0.17
     imperative
    0.16
     posible
    0.16
     advisable
    0.15
     unclear
    0.15
    possible
    0.14
     customary
    0.14
    Activations Density 0.813%

    No Known Activations