© 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. 89397
    Prev
    Next
    INDEX
    Explanations

    was supposed to be

    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
     surprisingly
    -0.13
     unexpectedly
    -0.12
    desired
    -0.11
     desired
    -0.11
     Sur
    -0.11
     oddly
    -0.10
     unexpected
    -0.10
    -sur
    -0.09
    sur
    -0.09
    kim
    -0.09
    POSITIVE LOGITS
     supposed
    0.17
     supposedly
    0.13
     babys
    0.10
     illust
    0.10
     impartial
    0.10
     allegedly
    0.10
     Nab
    0.10
     protected
    0.09
     Shan
    0.09
    iez
    0.09
    Activations Density 0.159%

    No Known Activations