© 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. 48612
    Prev
    Next
    INDEX
    Explanations

    on/off states

    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
     Prefer
    -0.12
    vez
    -0.11
     reunited
    -0.11
    zon
    -0.11
    419
    -0.10
     deactivate
    -0.10
     Drag
    -0.10
     ASAP
    -0.10
    imo
    -0.10
     preferably
    -0.10
    POSITIVE LOGITS
    fan
    0.09
     pied
    0.09
     McGill
    0.09
     delt
    0.08
     Walsh
    0.08
     downstairs
    0.07
     unas
    0.07
     bud
    0.07
     accessible
    0.07
     oval
    0.07
    Activations Density 0.006%

    No Known Activations