© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 17983
    Prev
    Next
    INDEX
    Explanations

    returning home or to work

    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
     Coming
    -0.13
     coming
    -0.12
    Coming
    -0.11
     originate
    -0.10
     compliant
    -0.10
    owo
    -0.10
     convinc
    -0.09
     slate
    -0.09
     incoming
    -0.09
     Buck
    -0.09
    POSITIVE LOGITS
     home
    0.11
     safely
    0.10
     late
    0.10
    ema
    0.09
     alive
    0.09
     Late
    0.09
    228
    0.09
    Late
    0.09
     courtesy
    0.09
    erna
    0.09
    Activations Density 0.027%

    No Known Activations