© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32087
    Prev
    Next
    INDEX
    Explanations

    python file headers

    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
     Daw
    -0.08
    ahoma
    -0.08
     Bonds
    -0.08
     Knox
    -0.08
     ste
    -0.07
    ircle
    -0.07
    unya
    -0.07
    efa
    -0.07
    ertia
    -0.07
    acin
    -0.07
    POSITIVE LOGITS
     Vance
    0.10
     Liberties
    0.09
     tempt
    0.09
    ...)↵
    0.09
     ----------↵
    0.09
    Fly
    0.09
    jid
    0.09
    cstdint
    0.09
     realities
    0.09
    ...");↵
    0.09
    Activations Density 0.280%

    No Known Activations