© 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. 88726
    Prev
    Next
    INDEX
    Explanations

    previous page

    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
     Grave
    -0.10
    cls
    -0.09
    forge
    -0.09
     Graves
    -0.09
    sim
    -0.08
     Lect
    -0.08
    alar
    -0.08
     [@
    -0.08
     Sim
    -0.08
    spir
    -0.08
    POSITIVE LOGITS
     earlier
    0.14
     aforementioned
    0.13
     previously
    0.11
     erst
    0.11
     anecd
    0.10
     Indust
    0.10
     afore
    0.10
     indeb
    0.10
     guit
    0.10
     previous
    0.09
    Activations Density 0.125%

    No Known Activations