© 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. 91369
    Prev
    Next
    INDEX
    Explanations

    yet low uptake

    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
     now
    -0.10
     rearr
    -0.10
     eventually
    -0.10
     hipp
    -0.09
     salv
    -0.09
    trying
    -0.09
     useless
    -0.09
     EVERY
    -0.09
     increasingly
    -0.08
     unavoid
    -0.08
    POSITIVE LOGITS
     neglect
    0.18
     ignorance
    0.16
     neglected
    0.15
     misunderstand
    0.15
     STILL
    0.15
     overlook
    0.15
     gaps
    0.15
     misunderstood
    0.14
     still
    0.14
     seldom
    0.14
    Activations Density 0.989%

    No Known Activations