© 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. 48948
    Prev
    Next
    INDEX
    Explanations

    To introduce actions or goals

    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
     Protest
    -0.08
    uras
    -0.08
    /mainwindow
    -0.08
    Prostit
    -0.08
     JNI
    -0.08
    "indices
    -0.08
     Beatles
    -0.07
    faker
    -0.07
    affles
    -0.07
     Boxing
    -0.07
    POSITIVE LOGITS
     download
    0.28
     Subscribe
    0.25
     Download
    0.25
     downloadable
    0.24
    Download
    0.24
     permalink
    0.23
     copyright
    0.23
     downloads
    0.23
     unsubscribe
    0.23
     subscribe
    0.22
    Activations Density 0.885%

    No Known Activations