© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28594
    Prev
    Next
    INDEX
    Explanations

    emergence of new technologies

    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
    izzer
    -0.11
    /manual
    -0.11
     ftp
    -0.10
     iconic
    -0.10
     Catholic
    -0.10
     Yugosl
    -0.10
     Playboy
    -0.10
     FTP
    -0.10
     Postal
    -0.10
     Baptist
    -0.10
    POSITIVE LOGITS
     blockchain
    0.25
     graphene
    0.23
     drones
    0.22
     IoT
    0.22
     Blockchain
    0.21
     Brexit
    0.21
     drone
    0.21
     cryptocurrencies
    0.20
     cryptocurrency
    0.19
     holog
    0.18
    Activations Density 4.564%

    No Known Activations