© 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. 16837
    Prev
    Next
    INDEX
    Explanations

    not good at

    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
    ofil
    -0.09
     unnecessarily
    -0.09
     obsc
    -0.08
     cann
    -0.08
     indul
    -0.08
     unusually
    -0.07
     nast
    -0.07
     vulner
    -0.07
     unexpectedly
    -0.07
     objection
    -0.07
    POSITIVE LOGITS
    rok
    0.13
     remembering
    0.12
     sarc
    0.12
     multit
    0.12
     notoriously
    0.12
     consistency
    0.12
     fines
    0.12
     endings
    0.11
    kus
    0.11
    wei
    0.11
    Activations Density 0.129%

    No Known Activations