© 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. 116382
    Prev
    Next
    INDEX
    Explanations

    stay tuned

    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
     dre
    -0.09
     continu
    -0.09
     Yo
    -0.09
    feel
    -0.09
    Manifest
    -0.08
    SF
    -0.08
     reluct
    -0.08
    iele
    -0.08
     tie
    -0.08
     manifest
    -0.08
    POSITIVE LOGITS
     tuned
    0.18
     Tun
    0.14
     hydrated
    0.14
     thirsty
    0.11
     classy
    0.11
     tune
    0.11
     tun
    0.11
     Alive
    0.10
    ahead
    0.10
     clam
    0.10
    Activations Density 0.013%

    No Known Activations