© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25042
    Prev
    Next
    INDEX
    Explanations

    moves to an interesting state

    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
    Negative Logits
     fuss
    -0.11
     intervening
    -0.10
     shel
    -0.10
     subsequent
    -0.10
     res
    -0.09
     initiate
    -0.09
     initiating
    -0.09
    ynom
    -0.09
     starting
    -0.08
    emet
    -0.08
    POSITIVE LOGITS
    izz
    0.12
    /person
    0.12
    amo
    0.11
     Blitz
    0.11
     focus
    0.11
    Personal
    0.11
    naz
    0.11
     squarely
    0.10
     Vij
    0.10
     focused
    0.10
    Activations Density 0.026%

    No Known Activations