© 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. 4276
    Prev
    Next
    INDEX
    Explanations

    is / remains / function / depends / include

    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
     means
    -0.11
     would
    -0.09
     Horn
    -0.08
     rocking
    -0.08
     bande
    -0.08
     could
    -0.08
     will
    -0.08
     reprodu
    -0.08
    means
    -0.08
     called
    -0.08
    POSITIVE LOGITS
     varies
    0.17
     vary
    0.15
     varied
    0.14
     fluct
    0.11
     ranges
    0.11
     depend
    0.11
     declines
    0.10
     depends
    0.09
    Yii
    0.09
     stays
    0.09
    Activations Density 0.522%

    No Known Activations