© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114236
    Prev
    Next
    INDEX
    Explanations

    know how to

    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
     recap
    -0.09
     Wagner
    -0.09
     Prest
    -0.08
    lo
    -0.08
    iris
    -0.08
     Cape
    -0.08
     tyr
    -0.08
     Gus
    -0.07
    .vm
    -0.07
     unsuccessfully
    -0.07
    POSITIVE LOGITS
     better
    0.32
    better
    0.29
     smarter
    0.29
     Better
    0.23
    Better
    0.23
     know
    0.20
    -know
    0.19
     mieux
    0.19
     knows
    0.19
     KNOW
    0.19
    Activations Density 0.131%

    No Known Activations