© 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. 25514
    Prev
    Next
    INDEX
    Explanations

    Georg + surname

    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
    herits
    -0.12
     lam
    -0.11
    éĻ¢
    -0.11
    anten
    -0.10
    xA
    -0.10
     Maid
    -0.10
     lamin
    -0.10
    xa
    -0.10
    eo
    -0.10
    odb
    -0.10
    POSITIVE LOGITS
    s
    0.09
     disposition
    0.09
     subsets
    0.08
    y
    0.08
    irsch
    0.07
    ie
    0.07
    ahan
    0.07
     parts
    0.07
    pick
    0.07
    anan
    0.07
    Activations Density 0.005%

    No Known Activations