© 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. 31184
    Prev
    Next
    INDEX
    Explanations

    high standards

    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
     peacefully
    -0.09
     badly
    -0.09
     fog
    -0.09
     wording
    -0.09
    undi
    -0.09
    extr
    -0.08
     Maxwell
    -0.08
     Gauss
    -0.08
    429
    -0.08
     und
    -0.08
    POSITIVE LOGITS
     standards
    0.23
     Standards
    0.17
     industry
    0.16
     safety
    0.14
    industry
    0.13
     ethical
    0.13
     strict
    0.13
     principles
    0.13
     stringent
    0.12
     excellence
    0.12
    Activations Density 0.042%

    No Known Activations