© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113528
    Prev
    Next
    INDEX
    Explanations

    prison, jail, cell, inmate, cage

    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
     surf
    -0.13
     RSVP
    -0.13
    faf
    -0.12
     tact
    -0.12
     Bene
    -0.11
     skiing
    -0.11
    ribbon
    -0.11
     balloons
    -0.11
     steep
    -0.11
     ski
    -0.11
    POSITIVE LOGITS
     cage
    0.30
     cell
    0.29
     inmate
    0.28
     jail
    0.28
     prison
    0.27
     inmates
    0.26
     prisoner
    0.25
     Jail
    0.25
     Cage
    0.25
     cages
    0.25
    Activations Density 0.143%

    No Known Activations