© 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. 33072
    Prev
    Next
    INDEX
    Explanations

    describing characteristics after 'the'

    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
    ationally
    -0.09
     candidacy
    -0.08
     constant
    -0.08
     bulk
    -0.08
    \Component
    -0.08
    ograph
    -0.08
    ivas
    -0.08
     Phillip
    -0.08
     unspecified
    -0.08
    kinson
    -0.08
    POSITIVE LOGITS
     nature
    0.29
     amount
    0.29
     way
    0.23
     manner
    0.23
     type
    0.22
     types
    0.22
     number
    0.21
     extent
    0.21
    nature
    0.21
     kinds
    0.19
    Activations Density 0.489%

    No Known Activations