© 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. 29143
    Prev
    Next
    INDEX
    Explanations

    study or stud

    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
    kir
    -0.10
     ATV
    -0.09
    gie
    -0.09
    imas
    -0.08
    cn
    -0.08
     sob
    -0.08
     Michaels
    -0.08
    ening
    -0.08
    utch
    -0.08
    ota
    -0.08
    POSITIVE LOGITS
    rary
    0.11
     abroad
    0.10
     habits
    0.10
     Julian
    0.10
     subj
    0.10
     atop
    0.10
    099
    0.09
    (er
    0.09
     Shack
    0.09
     muff
    0.09
    Activations Density 0.006%

    No Known Activations