© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4840
    Prev
    Next
    INDEX
    Explanations

    self-authenticating, guaranteed, concluded

    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
    Negative Logits
    acr
    -0.13
    etto
    -0.10
     nick
    -0.10
     rej
    -0.10
     unfamiliar
    -0.10
    азв
    -0.10
     tact
    -0.10
    -inter
    -0.09
     contextual
    -0.09
     motivations
    -0.09
    POSITIVE LOGITS
     predictable
    0.10
     deterministic
    0.10
     assured
    0.10
     Guarantee
    0.10
    elf
    0.09
     predetermined
    0.09
     elimination
    0.09
     truths
    0.09
     already
    0.09
     guaranteed
    0.09
    Activations Density 0.026%

    No Known Activations