© 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. 32659
    Prev
    Next
    INDEX
    Explanations

    communication and information

    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
     communications
    -0.26
     communication
    -0.25
     Communication
    -0.22
     Communications
    -0.21
     communicate
    -0.21
    Communication
    -0.20
     communicating
    -0.19
     communicates
    -0.18
     communicator
    -0.18
     communic
    -0.18
    POSITIVE LOGITS
    @Web
    0.10
    uga
    0.10
    DEM
    0.10
    yii
    0.09
    utan
    0.09
    ogan
    0.09
     Shared
    0.09
    ThreadPool
    0.09
     Serg
    0.09
    mysql
    0.09
    Activations Density 0.204%

    No Known Activations