© 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. 17659
    Prev
    Next
    INDEX
    Explanations

    no worries or problem

    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
    ouden
    -0.10
     lest
    -0.10
     Samar
    -0.10
     :(
    -0.10
    ???↵↵
    -0.10
     damn
    -0.09
    sein
    -0.09
     DAM
    -0.09
     Conservatives
    -0.09
     rightful
    -0.09
    POSITIVE LOGITS
     bree
    0.11
     prez
    0.09
    o
    0.09
     whatsoever
    0.09
    oid
    0.09
     rew
    0.09
    eyer
    0.09
     unusual
    0.09
     Meyer
    0.08
     fam
    0.08
    Activations Density 0.010%

    No Known Activations