© 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. 32097
    Prev
    Next
    INDEX
    Explanations

    limited or restricted

    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
    064
    -0.11
     Shortcut
    -0.11
    atem
    -0.10
     exem
    -0.10
    indr
    -0.10
    uale
    -0.10
     Ban
    -0.09
     privileges
    -0.09
     gusto
    -0.09
    changed
    -0.09
    POSITIVE LOGITS
     confines
    0.22
     constraints
    0.21
     rigid
    0.20
     constrained
    0.19
     constraint
    0.18
     shack
    0.18
     limited
    0.18
     restricted
    0.17
     confined
    0.17
     restrictive
    0.17
    Activations Density 0.085%

    No Known Activations