© 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. 87611
    Prev
    Next
    INDEX
    Explanations

    naked eye visibility/observation

    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
     salute
    -0.10
    ih
    -0.10
    /details
    -0.10
     ener
    -0.09
     ceremon
    -0.09
    ener
    -0.09
    -actions
    -0.09
    puty
    -0.09
    hil
    -0.09
    ENER
    -0.09
    POSITIVE LOGITS
     senses
    0.17
     sensors
    0.14
     telesc
    0.13
     microscope
    0.13
     eyes
    0.12
     telescope
    0.12
     imagination
    0.12
     curs
    0.12
     radar
    0.11
     cameras
    0.11
    Activations Density 0.154%

    No Known Activations