© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    musical vistas

    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
    odata
    -0.11
    iny
    -0.11
    ilst
    -0.10
    assoc
    -0.10
     Pad
    -0.10
     Foam
    -0.09
    banks
    -0.09
    azen
    -0.09
    shan
    -0.09
    lv
    -0.09
    POSITIVE LOGITS
    ism
    0.08
    ]|[
    0.08
     loose
    0.08
     mould
    0.07
     hus
    0.07
     definite
    0.07
     corrupt
    0.06
     courtesy
    0.06
     amid
    0.06
     drift
    0.06
    Activations Density 0.241%

    No Known Activations