© 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. 3377
    Prev
    Next
    INDEX
    Explanations

    specific locations

    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
     semen
    -0.11
     Nearby
    -0.10
     nearby
    -0.10
     massive
    -0.10
     ejaculation
    -0.10
    jd
    -0.10
     preempt
    -0.10
     Perry
    -0.10
    ún
    -0.10
     entrenched
    -0.09
    POSITIVE LOGITS
     kitchen
    0.12
     workplace
    0.12
     office
    0.11
     beach
    0.10
     ultimate
    0.10
     laboratory
    0.09
     classroom
    0.09
     streets
    0.08
    iest
    0.08
     Blanch
    0.08
    Activations Density 0.023%

    No Known Activations