© 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. 111667
    Prev
    Next
    INDEX
    Explanations

    start/release/switch on

    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
    Not in Any Lists

    No Comments

    Negative Logits
     unpack
    -0.11
     pickups
    -0.10
    iers
    -0.10
    arr
    -0.09
     arriving
    -0.09
     setup
    -0.08
    unpack
    -0.08
     Setup
    -0.08
     Grinding
    -0.08
     continue
    -0.08
    POSITIVE LOGITS
     countdown
    0.18
     Countdown
    0.16
     RELEASE
    0.14
     simultaneous
    0.13
    Release
    0.13
     simult
    0.13
     simultaneously
    0.13
     Release
    0.13
     releasing
    0.13
    /releases
    0.13
    Activations Density 0.099%

    No Known Activations