© 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. 113176
    Prev
    Next
    INDEX
    Explanations

    security vulnerabilities and exploitation

    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
     Daisy
    -0.09
     hookup
    -0.09
     tol
    -0.08
     Tran
    -0.08
     aisle
    -0.08
     licensed
    -0.08
     adhesive
    -0.08
     Shelf
    -0.08
     mio
    -0.08
    avl
    -0.07
    POSITIVE LOGITS
     attacker
    0.29
     attackers
    0.29
     vulnerabilities
    0.28
     vulnerability
    0.28
     Vulner
    0.27
     hacker
    0.27
     Attack
    0.26
     attack
    0.26
    Attack
    0.25
     exploit
    0.25
    Activations Density 1.582%

    No Known Activations