© 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. 25899
    Prev
    Next
    INDEX
    Explanations

    ste D.N.A

    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
     zw
    -0.08
    appa
    -0.08
    chooser
    -0.08
     Nous
    -0.08
     SF
    -0.08
     administr
    -0.08
    velt
    -0.08
    _accessible
    -0.08
     Erg
    -0.08
    vell
    -0.08
    POSITIVE LOGITS
     Delegate
    0.11
     Blockchain
    0.10
     Continent
    0.10
    finder
    0.10
     province
    0.10
    ronic
    0.10
    reste
    0.10
     reste
    0.10
     Hive
    0.10
    Delegate
    0.10
    Activations Density 0.016%

    No Known Activations