© 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. 116525
    Prev
    Next
    INDEX
    Explanations

    protecting what is wanted

    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
     brav
    -0.14
     bravery
    -0.10
     dart
    -0.10
     courageous
    -0.09
     squared
    -0.09
    ë¹Ħ
    -0.09
     courage
    -0.09
     mano
    -0.09
    nid
    -0.09
     nerv
    -0.09
    POSITIVE LOGITS
    protect
    0.12
     fucking
    0.12
     protecting
    0.11
     raping
    0.11
     rapes
    0.11
     kid
    0.11
     protect
    0.11
    dam
    0.11
     Protect
    0.11
     fucked
    0.10
    Activations Density 0.011%

    No Known Activations