© 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. 116788
    Prev
    Next
    INDEX
    Explanations

    reports and reviews

    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
    anko
    -0.10
    enze
    -0.09
    ventions
    -0.09
    halt
    -0.09
     implic
    -0.08
     clandest
    -0.08
    Licensed
    -0.08
     _$
    -0.08
    Disclosure
    -0.08
    rish
    -0.08
    POSITIVE LOGITS
     reviewers
    0.37
     critics
    0.36
     Critics
    0.29
     reportedly
    0.29
     commentators
    0.29
     reviews
    0.28
     complaints
    0.28
     complained
    0.28
     unanimously
    0.27
     reported
    0.27
    Activations Density 0.924%

    No Known Activations