© 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. 25818
    Prev
    Next
    INDEX
    Explanations

    premium quality or service

    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
    maker
    -0.12
    gro
    -0.12
    opo
    -0.11
    Specifications
    -0.11
    ihn
    -0.11
    otten
    -0.11
    ½æķ°
    -0.11
     Netz
    -0.11
    sey
    -0.11
    proof
    -0.11
    POSITIVE LOGITS
    -grade
    0.14
    -priced
    0.14
    -quality
    0.13
    ization
    0.12
    alto
    0.11
    grade
    0.11
    ize
    0.10
     grade
    0.10
     priced
    0.10
     Hog
    0.09
    Activations Density 0.014%

    No Known Activations