© 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. 47331
    Prev
    Next
    INDEX
    Explanations

    closed system or loop

    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
    cred
    -0.09
     enlarge
    -0.09
     legitimacy
    -0.08
     lim
    -0.08
     sacr
    -0.08
     enlarg
    -0.08
    ills
    -0.08
    alli
    -0.08
    tabs
    -0.08
    aug
    -0.07
    POSITIVE LOGITS
     Closed
    0.23
     closed
    0.20
     CLOSED
    0.19
    -loop
    0.19
    Closed
    0.17
    .closed
    0.17
    closed
    0.15
    .Closed
    0.15
    /Open
    0.14
     ended
    0.14
    Activations Density 0.101%

    No Known Activations