© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50978
    Prev
    Next
    INDEX
    Explanations

    benevolent or benedetto prefix

    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
    Negative Logits
    onn
    -0.10
    ToOne
    -0.08
    isa
    -0.08
     Ky
    -0.08
     Kimber
    -0.08
    ercul
    -0.08
     techn
    -0.08
     nons
    -0.08
     Mus
    -0.07
    ted
    -0.07
    POSITIVE LOGITS
     underneath
    0.11
    volent
    0.11
     beneath
    0.11
     infer
    0.11
    below
    0.10
     below
    0.10
     exterior
    0.10
    %',
    0.10
     omnip
    0.10
     fier
    0.10
    Activations Density 0.002%

    No Known Activations