© 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. 88962
    Prev
    Next
    INDEX
    Explanations

    Barack Obama or serious vulnerability

    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
     Escorts
    -0.08
     Absolute
    -0.06
     cotton
    -0.06
     Cotton
    -0.06
     Kaiser
    -0.06
     Diablo
    -0.06
     ri
    -0.06
    oha
    -0.06
     sphere
    -0.06
     Popular
    -0.06
    POSITIVE LOGITS
     Glo
    0.13
     vag
    0.12
     depreci
    0.12
     Graf
    0.12
     verm
    0.12
     vig
    0.11
     twins
    0.11
    alian
    0.11
     voluntary
    0.11
     Gallagher
    0.11
    Activations Density 0.041%

    No Known Activations