© 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. 4622
    Prev
    Next
    INDEX
    Explanations

    protection against threats

    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
    sealed
    -0.13
    vig
    -0.13
     sealed
    -0.12
     tapped
    -0.11
     fenced
    -0.10
     Bout
    -0.10
     Orth
    -0.10
     Hoy
    -0.10
     secretly
    -0.10
    ifen
    -0.10
    POSITIVE LOGITS
     protection
    0.22
     protect
    0.21
     Protection
    0.18
     shield
    0.17
    Protection
    0.16
     protects
    0.15
     shielding
    0.15
     protecting
    0.15
     protected
    0.14
     shields
    0.14
    Activations Density 0.075%

    No Known Activations