© 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. 15353
    Prev
    Next
    INDEX
    Explanations

    returning home

    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
    utas
    -0.11
    htag
    -0.09
    ogan
    -0.09
     bloc
    -0.09
    Encode
    -0.09
    quot
    -0.09
     ClassName
    -0.09
    plevel
    -0.09
     comprom
    -0.09
    /english
    -0.09
    POSITIVE LOGITS
     home
    0.38
     returning
    0.35
     hometown
    0.35
     return
    0.32
     returned
    0.30
    home
    0.29
     Returning
    0.29
    Returning
    0.28
     Home
    0.27
     HOME
    0.27
    Activations Density 0.243%

    No Known Activations