© 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. 47829
    Prev
    Next
    INDEX
    Explanations

    still + persistence or uncertainty

    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
     already
    -0.16
     still
    -0.15
     Still
    -0.14
     STILL
    -0.14
     Already
    -0.13
    Still
    -0.12
    already
    -0.12
    still
    -0.12
     eventually
    -0.11
    Already
    -0.10
    POSITIVE LOGITS
    etto
    0.11
    uns
    0.10
     uncont
    0.09
     better
    0.09
     underrated
    0.09
     Junction
    0.09
    mmo
    0.09
     pard
    0.09
    è®°
    0.09
    MIC
    0.09
    Activations Density 0.082%

    No Known Activations