© 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. 116967
    Prev
    Next
    INDEX
    Explanations

    -ing verbs followed by prepositional phrases

    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
    ldr
    -0.08
    usto
    -0.08
     intents
    -0.07
     Hag
    -0.07
     Day
    -0.06
    'll
    -0.06
    ’en
    -0.06
    DP
    -0.06
     Dispatch
    -0.06
    'en
    -0.06
    POSITIVE LOGITS
    redients
    0.13
    -wise
    0.11
    antz
    0.11
    byn
    0.11
     malt
    0.10
    Benef
    0.10
    cai
    0.10
    äºĨ
    0.10
    .mu
    0.10
    aban
    0.10
    Activations Density 0.086%

    No Known Activations