© 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. 113028
    Prev
    Next
    INDEX
    Explanations

    codes and licenses

    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
     &#
    -0.15
     comprised
    -0.12
     expansive
    -0.11
     preval
    -0.11
    ÃĤ
    -0.11
     comprise
    -0.11
     needing
    -0.11
     exceedingly
    -0.11
     terrific
    -0.11
     comprising
    -0.10
    POSITIVE LOGITS
    ãĥ»ãĥ»
    0.09
     Hardcore
    0.08
    -sama
    0.08
     Corona
    0.08
     espec
    0.08
     Consort
    0.08
     programmes
    0.08
     Stateless
    0.08
    âĻª
    0.07
     zak
    0.07
    Activations Density 0.004%

    No Known Activations