© 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. 16716
    Prev
    Next
    INDEX
    Explanations

    time indicators and read

    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
     Zuk
    -0.10
     Strikes
    -0.09
     Orr
    -0.09
     Geh
    -0.09
    NSS
    -0.09
     Cout
    -0.08
     Eis
    -0.08
     cuckold
    -0.08
     Authority
    -0.08
    ernes
    -0.08
    POSITIVE LOGITS
    lander
    0.10
     vc
    0.10
     lad
    0.10
     outlining
    0.10
     cle
    0.09
    TextBox
    0.09
     hosp
    0.09
     Hammer
    0.09
     Amph
    0.09
     con
    0.09
    Activations Density 0.413%

    No Known Activations