© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5701
    Prev
    Next
    INDEX
    Explanations

    COVID and Xbox systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŀĭ
    -0.08
    iry
    -0.08
     Mickey
    -0.08
     Peg
    -0.08
     everlasting
    -0.08
    -Col
    -0.08
     Kre
    -0.08
    burgh
    -0.08
     beetle
    -0.08
     Anal
    -0.07
    POSITIVE LOGITS
    uset
    0.11
     Orc
    0.09
    erin
    0.09
    /social
    0.09
     scor
    0.09
    atorium
    0.09
     chaud
    0.09
    rie
    0.09
     teil
    0.09
     patrol
    0.09
    Activations Density 0.020%

    No Known Activations