© 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. 14673
    Prev
    Next
    INDEX
    Explanations

    being kept waiting or left out

    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
     tac
    -0.10
    lox
    -0.10
     spir
    -0.10
    kal
    -0.10
     Funk
    -0.10
     Spir
    -0.10
     bless
    -0.09
     Mongo
    -0.09
     anonymously
    -0.09
     nom
    -0.09
    POSITIVE LOGITS
     waiting
    0.38
     Waiting
    0.31
    waiting
    0.28
     waited
    0.28
     waits
    0.27
     wait
    0.26
    Waiting
    0.26
     awaiting
    0.24
     WAIT
    0.22
    _waiting
    0.21
    Activations Density 0.170%

    No Known Activations