© 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. 48605
    Prev
    Next
    INDEX
    Explanations

    links to files and resources

    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
    Âł↵
    -0.08
     brav
    -0.08
    ationship
    -0.08
     vacant
    -0.08
     -↵
    -0.07
     duplex
    -0.07
    azer
    -0.07
     Jaw
    -0.07
     ,↵↵
    -0.07
    Ham
    -0.07
    POSITIVE LOGITS
    /community
    0.10
     Fans
    0.10
     inplace
    0.09
     mature
    0.09
    iloc
    0.09
    pz
    0.09
     fans
    0.09
    ||||
    0.09
    iert
    0.09
    reon
    0.09
    Activations Density 0.007%

    No Known Activations