© 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. 92370
    Prev
    Next
    INDEX
    Explanations

    question or next step

    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
     reasons
    -0.10
     Reasons
    -0.10
     trig
    -0.09
     Cli
    -0.09
     chic
    -0.08
    cion
    -0.08
     drawbacks
    -0.08
    marsh
    -0.08
     motive
    -0.08
     chalk
    -0.08
    POSITIVE LOGITS
     options
    0.18
     Options
    0.16
     Suggestions
    0.15
    gnore
    0.15
     option
    0.14
     suggestions
    0.14
    Options
    0.14
    Option
    0.14
     Option
    0.13
    action
    0.13
    Activations Density 0.104%

    No Known Activations