© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5679
    Prev
    Next
    INDEX
    Explanations

    committed to providing

    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
    395
    -0.11
    EA
    -0.11
    751
    -0.10
     amen
    -0.09
     enlist
    -0.09
     troub
    -0.09
     needing
    -0.09
     trusting
    -0.09
     braces
    -0.09
     prototypes
    -0.09
    POSITIVE LOGITS
     excellence
    0.20
     providing
    0.16
     Excellence
    0.14
     helping
    0.13
     ensuring
    0.13
     preserving
    0.12
     improving
    0.12
     serving
    0.12
     maintaining
    0.12
     delivering
    0.12
    Activations Density 0.036%

    No Known Activations