© 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. 55764
    Prev
    Next
    INDEX
    Explanations

    Actual claims, Actual response

    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
    iolet
    -0.09
    -fetch
    -0.09
    -multi
    -0.09
     Loose
    -0.09
    subj
    -0.09
     Prompt
    -0.09
     transports
    -0.09
    Scroll
    -0.09
     juste
    -0.09
     cél
    -0.09
    POSITIVE LOGITS
     judging
    0.09
    indy
    0.08
     akin
    0.08
     nothing
    0.08
     intended
    0.08
     Actual
    0.07
    aser
    0.07
    iet
    0.07
    meg
    0.07
     Jud
    0.07
    Activations Density 0.076%

    No Known Activations