© 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. 117041
    Prev
    Next
    INDEX
    Explanations

    sacred, divine, holy, protected, precious

    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
     conveniently
    -0.11
     compatible
    -0.10
    iced
    -0.10
    anse
    -0.10
    ej
    -0.10
     gar
    -0.09
     reliably
    -0.09
    Stone
    -0.09
     Borg
    -0.09
     orth
    -0.09
    POSITIVE LOGITS
     sacred
    0.35
     sac
    0.22
     Sacred
    0.22
     precious
    0.21
     sanct
    0.21
     delicate
    0.19
     holy
    0.18
     protected
    0.17
     confidential
    0.16
     sensitive
    0.16
    Activations Density 0.086%

    No Known Activations