© 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. 419
    Prev
    Next
    INDEX
    Explanations

    support for

    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
    Tu
    -0.10
    onium
    -0.09
    jal
    -0.09
    sharp
    -0.09
     Tu
    -0.09
     Gri
    -0.08
    owing
    -0.08
    rove
    -0.08
    iquer
    -0.08
    owns
    -0.08
    POSITIVE LOGITS
    ive
    0.18
    /support
    0.15
    iveness
    0.14
    ively
    0.13
    EncodingException
    0.12
    IVE
    0.12
    /op
    0.11
    ä»ĺ
    0.11
    /prom
    0.11
    æĮģ
    0.11
    Activations Density 0.624%

    No Known Activations