© 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. 5116
    Prev
    Next
    INDEX
    Explanations

    showing how 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
     nim
    -0.09
     SetUp
    -0.09
     persever
    -0.09
    eno
    -0.09
     clarification
    -0.09
    alus
    -0.09
    301
    -0.08
    kea
    -0.08
     Shen
    -0.08
     obs
    -0.08
    POSITIVE LOGITS
     empath
    0.34
     empathy
    0.31
     imagin
    0.26
     imagine
    0.24
     imagining
    0.23
     sympath
    0.22
     Imagine
    0.21
     put
    0.21
     Imag
    0.20
     Put
    0.20
    Activations Density 0.111%

    No Known Activations