© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54792
    Prev
    Next
    INDEX
    Explanations

    all participants in a specific group

    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
     divers
    -0.08
     diverse
    -0.08
     miscellaneous
    -0.08
     predomin
    -0.08
     including
    -0.08
    stor
    -0.07
     countless
    -0.07
    UGHT
    -0.07
    572
    -0.07
     Multiple
    -0.07
    POSITIVE LOGITS
     prefect
    0.10
    eldorf
    0.10
    åī
    0.10
     individually
    0.10
    complete
    0.10
    Remaining
    0.10
    -sur
    0.10
    .Completed
    0.10
    riot
    0.09
     caf
    0.09
    Activations Density 0.194%

    No Known Activations