© 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. 29725
    Prev
    Next
    INDEX
    Explanations

    preparing or making 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
     lik
    -0.10
     temporarily
    -0.09
     Ritch
    -0.08
    quin
    -0.08
     incl
    -0.08
    mite
    -0.08
     Imperial
    -0.08
    apur
    -0.08
     Signature
    -0.08
    edges
    -0.08
    POSITIVE LOGITS
    /un
    0.12
    wer
    0.10
    /ap
    0.10
     slugg
    0.10
    overe
    0.10
    hoot
    0.10
    boxes
    0.09
    -for
    0.09
     Outreach
    0.09
    Thought
    0.09
    Activations Density 0.017%

    No Known Activations