© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25737
    Prev
    Next
    INDEX
    Explanations

    communication system

    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
     Affero
    -0.10
     cigars
    -0.10
     favour
    -0.10
     ).↵↵
    -0.09
     neighbouring
    -0.09
     pawn
    -0.09
     dai
    -0.09
     justification
    -0.09
     Esk
    -0.09
     ),
    -0.09
    POSITIVE LOGITS
    gaard
    0.09
    ìĤ¬
    0.08
     slash
    0.08
    juan
    0.08
    Https
    0.08
     Yaz
    0.08
    .self
    0.08
     Week
    0.08
    /video
    0.08
     sideline
    0.08
    Activations Density 0.002%

    No Known Activations