© 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. 27164
    Prev
    Next
    INDEX
    Explanations

    why what even

    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
     really
    -0.12
     Dil
    -0.12
     REALLY
    -0.12
     pes
    -0.11
     downright
    -0.10
    ihn
    -0.10
     Really
    -0.10
     silly
    -0.10
    really
    -0.10
    ivil
    -0.10
    POSITIVE LOGITS
     even
    0.13
     EVEN
    0.11
     whatsoever
    0.10
    -even
    0.10
     autoc
    0.10
    even
    0.10
    enu
    0.09
     anywhere
    0.09
     WHATSOEVER
    0.09
    etta
    0.09
    Activations Density 0.132%

    No Known Activations