© 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. 47929
    Prev
    Next
    INDEX
    Explanations

    comparing things

    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
    fos
    -0.09
     remotely
    -0.08
    andy
    -0.08
    ieg
    -0.08
    azer
    -0.08
     externally
    -0.08
    isis
    -0.08
    ae
    -0.08
    nel
    -0.08
     Colleg
    -0.08
    POSITIVE LOGITS
     unlike
    0.88
     Unlike
    0.72
     compared
    0.69
    Unlike
    0.68
     Compared
    0.61
     differs
    0.45
     contrasts
    0.37
     contrast
    0.36
     differ
    0.35
    æ¯Ķ
    0.35
    Activations Density 2.917%

    No Known Activations