© 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. 32543
    Prev
    Next
    INDEX
    Explanations

    boundaries and limits

    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
    ige
    -0.11
     Coord
    -0.10
     coordination
    -0.10
    ih
    -0.09
     Mans
    -0.09
     assumption
    -0.09
     fulfill
    -0.09
     liaison
    -0.09
    éĽĨ
    -0.09
    ator
    -0.09
    POSITIVE LOGITS
     boundaries
    0.30
     boundary
    0.19
     borders
    0.19
     limits
    0.18
     Boundary
    0.17
     Bound
    0.16
    Boundary
    0.14
    boundary
    0.14
    limits
    0.14
     enforced
    0.14
    Activations Density 0.030%

    No Known Activations