© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8448
    Prev
    Next
    INDEX
    Explanations

    research review

    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
     experimenting
    -0.10
     experiment
    -0.08
     instrument
    -0.08
    paque
    -0.08
     experimentation
    -0.08
    experiment
    -0.08
     exped
    -0.08
    hey
    -0.08
    _setup
    -0.08
     bam
    -0.08
    POSITIVE LOGITS
     Topics
    0.12
     Trends
    0.12
     topics
    0.12
     reviewed
    0.11
     review
    0.11
     reviewing
    0.11
    CURRENT
    0.10
     discuss
    0.10
     briefly
    0.10
     discusses
    0.10
    Activations Density 0.236%

    No Known Activations