© 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. 27036
    Prev
    Next
    INDEX
    Explanations

    high energy

    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
     undisclosed
    -0.12
     Enough
    -0.11
     intentional
    -0.10
    optimized
    -0.10
     Composite
    -0.10
    onz
    -0.10
    iju
    -0.09
     unnamed
    -0.09
    Unnamed
    -0.09
     poisoned
    -0.09
    POSITIVE LOGITS
     often
    0.15
     famously
    0.14
     naturally
    0.13
     versatility
    0.13
     versatile
    0.13
     generally
    0.13
     unaffected
    0.12
     inert
    0.12
     usually
    0.11
     inherent
    0.11
    Activations Density 0.255%

    No Known Activations