© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    desire and intention

    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
    orgen
    -0.10
     Caj
    -0.10
    ares
    -0.09
     wa
    -0.09
     expire
    -0.09
     incur
    -0.09
    ahu
    -0.09
     inex
    -0.09
     Gift
    -0.08
     Wa
    -0.08
    POSITIVE LOGITS
     desperately
    0.10
     respect
    0.10
     neither
    0.10
     tempting
    0.10
     avoiding
    0.09
     resist
    0.09
     desper
    0.09
     grou
    0.09
     say
    0.09
     len
    0.09
    Activations Density 0.026%

    No Known Activations