© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27583
    Prev
    Next
    INDEX
    Explanations

    Association/Society names

    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
     Ministry
    -0.11
     OECD
    -0.10
     Department
    -0.09
    æĴ
    -0.08
     Async
    -0.08
     NASA
    -0.08
     Siemens
    -0.08
     Comet
    -0.08
    pii
    -0.08
     Municip
    -0.08
    POSITIVE LOGITS
     membership
    0.29
     Membership
    0.25
     member
    0.22
    membership
    0.22
    Membership
    0.22
     memberships
    0.22
     dues
    0.21
     members
    0.20
    .member
    0.19
    .org
    0.19
    Activations Density 1.712%

    No Known Activations