© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    change of state or circumstance

    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
    enta
    -0.10
    rok
    -0.09
     createdAt
    -0.09
    hawk
    -0.09
    erable
    -0.09
     spotted
    -0.09
    Credential
    -0.08
     recover
    -0.08
    mak
    -0.08
    ĵĺ
    -0.08
    POSITIVE LOGITS
     exposure
    0.13
     suddenly
    0.12
     unrestricted
    0.11
     Exposure
    0.11
     free
    0.11
     deprived
    0.10
     confronted
    0.10
     Fam
    0.10
     forced
    0.10
     sudden
    0.10
    Activations Density 0.299%

    No Known Activations