© 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. 48699
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying degree or condition

    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
     Baz
    -0.12
    ly
    -0.11
    reas
    -0.09
    ,
    -0.08
    ign
    -0.08
    -minus
    -0.08
    -available
    -0.07
     Atl
    -0.07
    ely
    -0.07
    ÅĦ
    -0.07
    POSITIVE LOGITS
    trib
    0.10
     milano
    0.10
    ombat
    0.10
    massage
    0.09
    ><![
    0.09
    MainThread
    0.09
    uraa
    0.09
     Wend
    0.09
    anchor
    0.09
    urement
    0.09
    Activations Density 0.277%

    No Known Activations