© 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. 48637
    Prev
    Next
    INDEX
    Explanations

    academic conference

    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
    cola
    -0.12
     rumored
    -0.11
     amateurs
    -0.10
    [âĢ¦
    -0.09
     weblog
    -0.09
     oe
    -0.09
    unden
    -0.09
     COMMENTS
    -0.09
     online
    -0.09
     cab
    -0.09
    POSITIVE LOGITS
    Lorem
    0.12
     :)↵↵
    0.09
     âĿ¤
    0.09
     LTD
    0.09
     :)
    0.09
     kindly
    0.09
     discord
    0.09
     Voyage
    0.08
    ï¸ı
    0.08
     Ain
    0.08
    Activations Density 0.079%

    No Known Activations