© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30933
    Prev
    Next
    INDEX
    Explanations

    look for, look at

    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
     Vance
    -0.12
     gradual
    -0.11
    uales
    -0.09
     increment
    -0.09
     pacing
    -0.09
    umba
    -0.09
     Ear
    -0.09
     incremental
    -0.08
     Increment
    -0.08
     toen
    -0.08
    POSITIVE LOGITS
    -threat
    0.10
     Epstein
    0.10
     stray
    0.09
     '../../../../../
    0.09
     zoek
    0.09
    lob
    0.09
    &o
    0.09
     massa
    0.09
     eens
    0.08
     Blessed
    0.08
    Activations Density 0.001%

    No Known Activations