© 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. 705
    Prev
    Next
    INDEX
    Explanations

    again and also

    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
     anyway
    -0.11
     anyhow
    -0.11
     anyways
    -0.10
    otte
    -0.09
    ROC
    -0.09
    redo
    -0.09
    ISA
    -0.09
     arch
    -0.09
     Hä
    -0.09
     indeed
    -0.09
    POSITIVE LOGITS
     similarly
    0.12
     victim
    0.09
    Same
    0.08
     problematic
    0.08
    ound
    0.08
     albeit
    0.08
    ¥
    0.08
     another
    0.08
     same
    0.08
     Assist
    0.08
    Activations Density 0.739%

    No Known Activations