© 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. 27951
    Prev
    Next
    INDEX
    Explanations

    roles and switching

    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
     secluded
    -0.12
     liv
    -0.12
     living
    -0.12
     Locale
    -0.11
     live
    -0.11
     surreal
    -0.11
     Surround
    -0.11
     sanitized
    -0.11
     censor
    -0.10
     surrounding
    -0.10
    POSITIVE LOGITS
     roles
    0.19
     switch
    0.17
     switching
    0.16
     Roles
    0.16
     role
    0.16
     switches
    0.15
    roles
    0.15
    Roles
    0.14
     topping
    0.14
     ego
    0.14
    Activations Density 0.085%

    No Known Activations