© 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. 28573
    Prev
    Next
    INDEX
    Explanations

    enclosures, pens, and confinement

    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
     hors
    -0.11
     paras
    -0.10
    chap
    -0.10
    owie
    -0.10
     umb
    -0.09
    Stub
    -0.09
    isu
    -0.09
    	diff
    -0.09
     lint
    -0.09
     dead
    -0.09
    POSITIVE LOGITS
     cage
    0.21
     cages
    0.19
     confinement
    0.18
     confined
    0.14
     deprived
    0.13
     Cage
    0.13
     zoo
    0.12
     avi
    0.11
     confines
    0.11
     breeding
    0.11
    Activations Density 0.031%

    No Known Activations