© 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. 15734
    Prev
    Next
    INDEX
    Explanations

    private, secluded, or isolated settings

    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
    Äĥr
    -0.09
     Align
    -0.08
    .fun
    -0.08
     pathological
    -0.08
     align
    -0.08
     flatt
    -0.08
     Irr
    -0.08
    ouser
    -0.08
     polishing
    -0.08
     cripp
    -0.08
    POSITIVE LOGITS
     privacy
    0.38
     secluded
    0.35
     isolation
    0.31
     isolated
    0.29
     Privacy
    0.29
    privacy
    0.29
    Privacy
    0.28
     isol
    0.25
    isol
    0.24
     confidentiality
    0.24
    Activations Density 0.046%

    No Known Activations