© 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. 112484
    Prev
    Next
    INDEX
    Explanations

    increasingly growing now

    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
     eventually
    -0.14
    Eventually
    -0.14
     afterwards
    -0.13
     initially
    -0.13
     eventual
    -0.12
     subsequently
    -0.11
     Initially
    -0.11
     ultimately
    -0.11
     Eventually
    -0.11
     afterward
    -0.10
    POSITIVE LOGITS
     now
    0.28
     increasingly
    0.25
     growing
    0.22
    now
    0.21
     Now
    0.18
     still
    0.17
     nearing
    0.17
    Now
    0.17
     Growing
    0.17
     increasing
    0.17
    Activations Density 0.080%

    No Known Activations