© 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. 26504
    Prev
    Next
    INDEX
    Explanations

    permission and authorization

    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
    ica
    -0.09
     unlikely
    -0.09
     Influ
    -0.08
    iasm
    -0.08
     surre
    -0.08
    iom
    -0.08
    pell
    -0.08
     insisting
    -0.08
     Integrity
    -0.07
    dera
    -0.07
    POSITIVE LOGITS
     authorization
    0.16
     permission
    0.16
     authorize
    0.14
    chg
    0.11
    Permission
    0.11
     Pang
    0.11
     invitation
    0.11
     Authorization
    0.10
     instructed
    0.10
     Bast
    0.10
    Activations Density 0.003%

    No Known Activations