© 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. 91453
    Prev
    Next
    INDEX
    Explanations

    uncoupling protein, growth factor, differentiation, incorporation

    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
     uncert
    -0.12
     explic
    -0.11
     honest
    -0.11
     creds
    -0.11
     personally
    -0.11
     cred
    -0.11
    venture
    -0.10
    лиÑĨ
    -0.10
     $($
    -0.10
     embell
    -0.10
    POSITIVE LOGITS
     cells
    0.12
     physiological
    0.11
     bacteria
    0.11
     metabol
    0.10
     pornstar
    0.10
     schöne
    0.10
     inflammation
    0.10
     tissue
    0.10
     follic
    0.09
     metabolic
    0.09
    Activations Density 28.344%

    No Known Activations