© 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. 28772
    Prev
    Next
    INDEX
    Explanations

    used to

    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
     tonight
    -0.12
     today
    -0.12
    ä»Ĭå¹´
    -0.11
     later
    -0.11
     recent
    -0.11
    already
    -0.10
     again
    -0.10
     anew
    -0.10
     yet
    -0.10
     inaugural
    -0.10
    POSITIVE LOGITS
     Former
    0.15
    avin
    0.12
     formerly
    0.11
    Former
    0.11
     Now
    0.11
     circa
    0.10
    Now
    0.10
     regularly
    0.10
     occasionally
    0.10
     old
    0.10
    Activations Density 0.100%

    No Known Activations