© 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. 27143
    Prev
    Next
    INDEX
    Explanations

    light from openings and features

    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
     Gron
    -0.10
     progressing
    -0.09
     Supern
    -0.09
    ographies
    -0.09
    oge
    -0.09
     Kunst
    -0.09
    utan
    -0.09
     multid
    -0.09
    osed
    -0.09
     myself
    -0.09
    POSITIVE LOGITS
     illumin
    0.11
     nearby
    0.10
     shines
    0.10
     irradi
    0.09
     mktime
    0.09
    oren
    0.09
     occasional
    0.09
     stationed
    0.09
     gently
    0.09
     contrasts
    0.09
    Activations Density 0.010%

    No Known Activations