© 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. 90488
    Prev
    Next
    INDEX
    Explanations

    shades of color

    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
    tas
    -0.10
    ertia
    -0.10
    ural
    -0.10
     Tenn
    -0.10
    lds
    -0.10
    auc
    -0.10
     minded
    -0.10
    icas
    -0.10
    ace
    -0.10
    Mind
    -0.10
    POSITIVE LOGITS
    /color
    0.12
     darker
    0.09
    forth
    0.09
    pire
    0.08
    bill
    0.08
     Central
    0.08
     lighter
    0.08
    vos
    0.08
    elay
    0.08
    -tree
    0.08
    Activations Density 0.011%

    No Known Activations