© 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. 90526
    Prev
    Next
    INDEX
    Explanations

    'm/is/am/was + present participle

    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
     numbering
    -0.10
     handic
    -0.09
     Brad
    -0.08
    birthdate
    -0.08
     encountered
    -0.08
     experiences
    -0.08
    IVO
    -0.08
     suffer
    -0.08
     multic
    -0.08
     Cho
    -0.08
    POSITIVE LOGITS
     interested
    0.12
     interest
    0.12
    UND
    0.11
     pursuing
    0.10
     interes
    0.10
     supposed
    0.10
     Interested
    0.10
     interests
    0.10
    (async
    0.10
    527
    0.10
    Activations Density 0.015%

    No Known Activations