© 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. 111477
    Prev
    Next
    INDEX
    Explanations

    operating systems and platforms

    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
    assin
    -0.10
     prospect
    -0.09
     wanna
    -0.09
    itus
    -0.09
    elder
    -0.08
    notation
    -0.08
    oman
    -0.08
    isd
    -0.08
    .prop
    -0.08
     tent
    -0.08
    POSITIVE LOGITS
     platforms
    0.22
     users
    0.19
     owners
    0.18
     devices
    0.16
     systems
    0.16
     machines
    0.15
     computers
    0.14
     Platforms
    0.14
     Owners
    0.14
     platform
    0.13
    Activations Density 0.807%

    No Known Activations