© 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. 50525
    Prev
    Next
    INDEX
    Explanations

    held accountable or contained

    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
    cae
    -0.09
     paraph
    -0.08
     power
    -0.08
     cert
    -0.08
     Power
    -0.07
    odb
    -0.07
    ardon
    -0.07
     left
    -0.07
     sunshine
    -0.07
     avent
    -0.07
    POSITIVE LOGITS
     captive
    0.19
     hostage
    0.16
     sway
    0.14
     ransom
    0.14
     prisoner
    0.13
     contempt
    0.13
     controlled
    0.12
     contained
    0.11
     captivity
    0.11
     Bail
    0.11
    Activations Density 0.045%

    No Known Activations