© 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. 47646
    Prev
    Next
    INDEX
    Explanations

    privacy and concealment

    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
     Pace
    -0.10
     Sadd
    -0.10
    Bru
    -0.10
     pulse
    -0.10
     Bru
    -0.10
    iasm
    -0.10
     stamps
    -0.10
     dorm
    -0.10
     bru
    -0.09
     asynchronously
    -0.09
    POSITIVE LOGITS
     obsc
    0.40
     conceal
    0.39
     hiding
    0.37
     shielding
    0.36
     cover
    0.36
     hides
    0.33
     covering
    0.33
     masking
    0.33
     opaque
    0.32
     hide
    0.32
    Activations Density 0.284%

    No Known Activations