© 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. 31370
    Prev
    Next
    INDEX
    Explanations

    "TED" Talks or by authors

    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
     overshadow
    -0.10
     spiritually
    -0.10
     Records
    -0.09
     oppressive
    -0.09
     prolet
    -0.09
    oute
    -0.09
     belie
    -0.09
     Generic
    -0.09
     inexperienced
    -0.09
     hollow
    -0.08
    POSITIVE LOGITS
     neuroscience
    0.26
     scientifically
    0.23
     Neuroscience
    0.22
     TED
    0.22
     science
    0.22
     evolutionary
    0.20
    TED
    0.19
    science
    0.19
    Science
    0.19
     scientific
    0.19
    Activations Density 0.759%

    No Known Activations