© 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. 33187
    Prev
    Next
    INDEX
    Explanations

    searching for ways

    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
     Brill
    -0.11
    ensions
    -0.10
     McK
    -0.10
     unsupported
    -0.10
     Undefined
    -0.10
    ragen
    -0.10
     intolerance
    -0.10
    abit
    -0.09
    ika
    -0.09
    ï¼Īç¬ij
    -0.09
    POSITIVE LOGITS
     ways
    0.21
     desperately
    0.17
     searched
    0.17
     search
    0.16
     searching
    0.16
     devis
    0.16
     searches
    0.16
     devise
    0.15
     Ways
    0.15
    -search
    0.15
    Activations Density 0.155%

    No Known Activations