© 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. 47788
    Prev
    Next
    INDEX
    Explanations

    enough

    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
     tow
    -0.09
    249
    -0.08
     Cheat
    -0.07
     globalization
    -0.07
     cust
    -0.07
    posit
    -0.07
     sorts
    -0.06
     whe
    -0.06
     HG
    -0.06
    itos
    -0.06
    POSITIVE LOGITS
     enough
    0.14
     money
    0.12
    rah
    0.12
     Rah
    0.12
     Enough
    0.11
    ihan
    0.11
     Assembly
    0.11
     anymore
    0.11
    !/
    0.11
     maka
    0.11
    Activations Density 0.002%

    No Known Activations