© 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. 48045
    Prev
    Next
    INDEX
    Explanations

    strongly positive adjectives

    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
     anymore
    -0.12
     properly
    -0.11
    hir
    -0.11
     whom
    -0.10
     remotely
    -0.10
     Virt
    -0.10
     systematic
    -0.10
     orally
    -0.10
     indiscrim
    -0.10
     IGN
    -0.10
    POSITIVE LOGITS
     immensely
    0.26
     greatly
    0.24
     tremendously
    0.21
     definitely
    0.19
     enormously
    0.19
     considerably
    0.18
     absolutely
    0.16
     Definitely
    0.16
     dearly
    0.15
     vastly
    0.15
    Activations Density 0.097%

    No Known Activations