© 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. 88610
    Prev
    Next
    INDEX
    Explanations

    strange transformations and growth

    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
     eternal
    -0.10
     dam
    -0.10
     reflex
    -0.10
     trespass
    -0.09
     grace
    -0.09
     Klein
    -0.09
     gaz
    -0.09
     occult
    -0.09
     Bian
    -0.08
    aed
    -0.08
    POSITIVE LOGITS
     vines
    0.14
     pedestal
    0.11
    enga
    0.11
     formed
    0.10
     whirl
    0.10
     swell
    0.10
     formations
    0.10
     vine
    0.10
     manifestations
    0.10
     tendr
    0.10
    Activations Density 0.059%

    No Known Activations