© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8323
    Prev
    Next
    INDEX
    Explanations

    on the

    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
    Negative Logits
    agara
    -0.09
    lag
    -0.08
     Jonathan
    -0.07
     Elder
    -0.07
     VX
    -0.07
    uta
    -0.07
     Forward
    -0.07
     untreated
    -0.07
     Hiro
    -0.07
     bridge
    -0.07
    POSITIVE LOGITS
    uhl
    0.11
    abouts
    0.10
     Lomb
    0.10
     tame
    0.10
     minced
    0.10
     trot
    0.10
     Sutton
    0.10
    ạn
    0.10
    oram
    0.10
    Runs
    0.10
    Activations Density 0.016%

    No Known Activations