© 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. 32398
    Prev
    Next
    INDEX
    Explanations

    better yet, or worse still

    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
     Bou
    -0.09
     Coleman
    -0.09
    /fl
    -0.08
    anken
    -0.08
    avier
    -0.08
    pike
    -0.08
    ysi
    -0.08
     bou
    -0.08
    bum
    -0.08
    LOT
    -0.08
    POSITIVE LOGITS
     better
    0.71
     Better
    0.60
    better
    0.59
    Better
    0.56
     mejor
    0.38
     mieux
    0.37
     besser
    0.36
     melhor
    0.34
    etter
    0.30
     BET
    0.27
    Activations Density 0.199%

    No Known Activations