© 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. 50067
    Prev
    Next
    INDEX
    Explanations

    no pets, firearms, or smoking

    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
    imas
    -0.09
     forgiving
    -0.09
     Amb
    -0.09
     downward
    -0.09
     Loren
    -0.09
     vic
    -0.08
     CONTEXT
    -0.08
     mas
    -0.08
     overseas
    -0.08
    itsu
    -0.08
    POSITIVE LOGITS
     prohibited
    0.19
     unauthorized
    0.18
     visitors
    0.16
     smoking
    0.16
     permitted
    0.16
     banned
    0.16
     Unauthorized
    0.16
     Smoking
    0.15
     Bring
    0.14
     disruptive
    0.14
    Activations Density 0.166%

    No Known Activations