© 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. 88651
    Prev
    Next
    INDEX
    Explanations

    professional fields

    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
    ori
    -0.10
    borne
    -0.09
    forgettable
    -0.09
    -loving
    -0.09
    joy
    -0.09
     Attr
    -0.09
    ventions
    -0.09
    lets
    -0.08
     finalized
    -0.08
     Commod
    -0.08
    POSITIVE LOGITS
     courtesy
    0.16
    ism
    0.13
     mour
    0.13
     Courtesy
    0.13
    -grade
    0.13
     misconduct
    0.12
    /person
    0.12
     wrestling
    0.12
     gamb
    0.11
     Development
    0.11
    Activations Density 0.039%

    No Known Activations