© 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. 113664
    Prev
    Next
    INDEX
    Explanations

    in light of

    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
    elden
    -0.11
     Reyn
    -0.11
     overse
    -0.11
    oute
    -0.10
    assin
    -0.10
     Moss
    -0.09
    aver
    -0.09
    edm
    -0.09
    minus
    -0.09
     realm
    -0.09
    POSITIVE LOGITS
     recent
    0.15
     evidence
    0.12
     impending
    0.11
     mounting
    0.10
     developments
    0.10
     looming
    0.10
     findings
    0.10
     Recent
    0.10
     upcoming
    0.10
     revelations
    0.09
    Activations Density 0.065%

    No Known Activations