© 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. 17142
    Prev
    Next
    INDEX
    Explanations

    measures change or extent

    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
    -vars
    -0.13
    ulan
    -0.12
    uploader
    -0.11
     disappe
    -0.11
     nin
    -0.11
     blat
    -0.11
    ysi
    -0.11
     Prem
    -0.11
     Useful
    -0.11
     Concrete
    -0.10
    POSITIVE LOGITS
     mere
    0.40
     merely
    0.36
     simple
    0.30
     slightest
    0.30
     simply
    0.27
     modest
    0.26
    mere
    0.24
     just
    0.24
    simple
    0.22
     even
    0.22
    Activations Density 0.662%

    No Known Activations