© 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. 56248
    Prev
    Next
    INDEX
    Explanations

    lasting long-term indefinite

    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
    oles
    -0.10
     turbulent
    -0.08
     bloody
    -0.08
     briefly
    -0.08
     te
    -0.08
    blood
    -0.08
     prec
    -0.08
     rapid
    -0.08
     Blanc
    -0.08
    Äij
    -0.08
    POSITIVE LOGITS
     perman
    0.23
     permanent
    0.21
     permanently
    0.20
     indefinitely
    0.19
     Permanent
    0.19
     persistence
    0.19
     persistent
    0.19
     lasting
    0.18
     lifelong
    0.18
     Forever
    0.18
    Activations Density 0.181%

    No Known Activations