© 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. 2108
    Prev
    Next
    INDEX
    Explanations

    "via" or "against"

    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
    achs
    -0.09
    nder
    -0.08
    ros
    -0.08
    ika
    -0.08
     Pier
    -0.08
    ender
    -0.08
    ukt
    -0.08
    enders
    -0.07
    iph
    -0.07
    'h
    -0.07
    POSITIVE LOGITS
     saddle
    0.09
     Doing
    0.09
     yourselves
    0.09
    leigh
    0.09
    396
    0.09
     Toledo
    0.09
     Frost
    0.09
    397
    0.09
     via
    0.09
    Äĥr
    0.08
    Activations Density 0.721%

    No Known Activations