© 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. 47843
    Prev
    Next
    INDEX
    Explanations

    play hard, active lifestyle

    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
    541
    -0.11
     kissed
    -0.10
     touching
    -0.10
     barber
    -0.10
     sincerity
    -0.10
     Incre
    -0.10
     involuntary
    -0.10
    abet
    -0.10
     coached
    -0.10
    asd
    -0.10
    POSITIVE LOGITS
     nightlife
    0.31
     fun
    0.28
     party
    0.25
     recreational
    0.25
     entertainment
    0.23
     recreation
    0.23
     leisure
    0.23
     Fun
    0.23
     parties
    0.22
     PARTY
    0.22
    Activations Density 0.161%

    No Known Activations