© 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. 56690
    Prev
    Next
    INDEX
    Explanations

    `core` followed by path separators

    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
    IAS
    -0.09
    tery
    -0.09
    ional
    -0.09
    éis
    -0.09
    axes
    -0.09
    agi
    -0.09
    ÑĤеÑĢ
    -0.09
    WEB
    -0.09
    rack
    -0.09
    tdown
    -0.09
    POSITIVE LOGITS
    nero
    0.08
    auc
    0.08
    íģ¬
    0.08
    icher
    0.08
    eu
    0.08
     Hai
    0.08
    anko
    0.07
     purification
    0.07
    ede
    0.07
    elo
    0.07
    Activations Density 0.002%

    No Known Activations