© 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. 91765
    Prev
    Next
    INDEX
    Explanations

    actions or states that happen to things

    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
     self
    -0.11
     concurrently
    -0.11
     Self
    -0.10
    hee
    -0.10
     brav
    -0.09
     favour
    -0.09
     legitim
    -0.09
     fav
    -0.09
    .self
    -0.09
     sac
    -0.09
    POSITIVE LOGITS
     manually
    0.14
     painstaking
    0.14
     forcibly
    0.14
     gently
    0.13
     carefully
    0.12
     gentle
    0.11
    vern
    0.11
     careful
    0.11
     outdoors
    0.11
    /ca
    0.11
    Activations Density 0.008%

    No Known Activations