© 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. 54245
    Prev
    Next
    INDEX
    Explanations

    despite advances or improved

    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
     justified
    -0.09
    lage
    -0.08
    atus
    -0.08
     Solo
    -0.08
     luc
    -0.08
     vain
    -0.08
     Recent
    -0.08
     depleted
    -0.08
    ipt
    -0.08
     justify
    -0.08
    POSITIVE LOGITS
    christ
    0.10
    ipa
    0.10
     moderated
    0.10
     crib
    0.10
    unan
    0.09
     seri
    0.09
    UTTON
    0.09
    erable
    0.09
    cri
    0.09
     moderation
    0.09
    Activations Density 0.064%

    No Known Activations