© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 29045
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     prospect
    -0.11
     decis
    -0.09
     Pers
    -0.09
     vars
    -0.08
     unprecedented
    -0.08
    981
    -0.08
     Capability
    -0.08
     prospects
    -0.08
     Mong
    -0.08
     Cabr
    -0.08
    POSITIVE LOGITS
     easier
    0.16
    accom
    0.11
     accesses
    0.11
     better
    0.11
     ease
    0.11
    asier
    0.11
    -access
    0.11
     Maxim
    0.10
    ɵ
    0.10
    better
    0.10
    Activations Density 0.000%

    No Known Activations