© 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. 4723
    Prev
    Next
    INDEX
    Explanations

    holding, restraining, escorting

    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
     revital
    -0.12
     assass
    -0.11
     Bened
    -0.11
     Wag
    -0.11
     wag
    -0.11
     faithfully
    -0.11
    uros
    -0.11
     Ping
    -0.11
     assassination
    -0.11
    orgen
    -0.11
    POSITIVE LOGITS
     overpower
    0.17
     wrest
    0.16
     restraint
    0.14
     restraining
    0.13
     restr
    0.13
     locking
    0.13
     hold
    0.13
     holding
    0.13
     restrain
    0.13
     Holding
    0.13
    Activations Density 0.018%

    No Known Activations