© 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. 89348
    Prev
    Next
    INDEX
    Explanations

    restrictions and allowances

    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
     lone
    -0.10
    osten
    -0.10
     singleton
    -0.10
     perish
    -0.09
    oka
    -0.09
     anch
    -0.09
    umn
    -0.09
     recognizable
    -0.09
    eya
    -0.09
     anchor
    -0.09
    POSITIVE LOGITS
     zones
    0.19
     Zones
    0.15
     segreg
    0.15
     enforced
    0.14
     zone
    0.14
     designated
    0.14
     tolerance
    0.14
     permitted
    0.14
     allowed
    0.14
     tolerant
    0.13
    Activations Density 0.041%

    No Known Activations