© 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. 33017
    Prev
    Next
    INDEX
    Explanations

    related to its or their

    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
    arra
    -0.10
    –and
    -0.08
    rov
    -0.08
    orest
    -0.08
    odzi
    -0.08
    itaire
    -0.08
    ibel
    -0.08
    sel
    -0.08
     Chips
    -0.07
    ault
    -0.07
    POSITIVE LOGITS
     ilk
    0.27
     associated
    0.19
     associates
    0.19
     derivatives
    0.18
     allies
    0.18
     accompanying
    0.17
     accessories
    0.17
     affiliates
    0.16
     surroundings
    0.16
     attendant
    0.15
    Activations Density 0.183%

    No Known Activations