© 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. 90026
    Prev
    Next
    INDEX
    Explanations

    browser status or recent change

    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
     Went
    -0.14
     underwent
    -0.12
     atm
    -0.12
    amac
    -0.11
    pls
    -0.11
     saw
    -0.11
     Tib
    -0.10
    ami
    -0.10
    did
    -0.10
    eling
    -0.10
    POSITIVE LOGITS
     gotten
    0.21
     been
    0.18
     lately
    0.18
     fallen
    0.16
    been
    0.15
     gone
    0.15
     recently
    0.13
     undergone
    0.13
     risen
    0.13
     earlier
    0.13
    Activations Density 2.283%

    No Known Activations