© 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. 7370
    Prev
    Next
    INDEX
    Explanations

    still continuing

    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
     suddenly
    -0.13
    isko
    -0.12
     Ire
    -0.12
     consort
    -0.11
     become
    -0.11
     Hob
    -0.11
     pylint
    -0.11
    orsi
    -0.11
    bec
    -0.11
     Become
    -0.11
    POSITIVE LOGITS
     maintained
    0.11
     previous
    0.11
     maintaining
    0.10
     remains
    0.10
     maintains
    0.10
     puzzled
    0.09
     earlier
    0.09
    æľª
    0.09
     intact
    0.09
     undecided
    0.09
    Activations Density 0.029%

    No Known Activations