© 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. 49915
    Prev
    Next
    INDEX
    Explanations

    time and duration

    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
     RESP
    -0.10
    -II
    -0.10
     Werner
    -0.09
     TLC
    -0.09
    estr
    -0.09
     CWE
    -0.09
    _overflow
    -0.09
     III
    -0.09
     Richie
    -0.09
    ós
    -0.09
    POSITIVE LOGITS
     depress
    0.09
     fancy
    0.09
    /up
    0.09
     Epstein
    0.09
     Communication
    0.09
     hollow
    0.08
    eva
    0.08
     hatch
    0.08
    .modules
    0.08
    ĸ
    0.08
    Activations Density 0.001%

    No Known Activations