© 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. 4771
    Prev
    Next
    INDEX
    Explanations

    function ready lock Cumberland resonance

    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
     POSS
    -0.11
     enthusi
    -0.11
     posible
    -0.11
     safeg
    -0.10
    mente
    -0.10
     helf
    -0.10
     nack
    -0.10
     willing
    -0.10
     sucess
    -0.10
     acknow
    -0.10
    POSITIVE LOGITS
     essay
    0.09
     rer
    0.09
    Islam
    0.09
     re
    0.09
     set
    0.08
     undergo
    0.08
     envis
    0.08
     prze
    0.08
     Lam
    0.08
     le
    0.08
    Activations Density 0.068%

    No Known Activations