© 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. 115537
    Prev
    Next
    INDEX
    Explanations

    total and cumulative counts

    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
     surroundings
    -0.10
     bum
    -0.10
     chop
    -0.09
    anza
    -0.09
    massage
    -0.08
     Eck
    -0.08
     Scha
    -0.08
     Pest
    -0.08
     precondition
    -0.08
    987
    -0.08
    POSITIVE LOGITS
     total
    0.35
    total
    0.27
     Total
    0.26
    Total
    0.25
     average
    0.23
    _total
    0.23
     number
    0.22
     cumulative
    0.22
    -total
    0.21
    	total
    0.21
    Activations Density 1.323%

    No Known Activations