© 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. 114437
    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
    ripp
    -0.10
     Wheat
    -0.10
     Pratt
    -0.10
    awl
    -0.10
     Concurrent
    -0.10
    ogn
    -0.10
    ört
    -0.09
     pled
    -0.09
     Timothy
    -0.09
    awan
    -0.09
    POSITIVE LOGITS
     return
    0.39
     returning
    0.38
     home
    0.38
    return
    0.34
     Return
    0.32
     Returning
    0.30
    -return
    0.29
    home
    0.29
    Return
    0.28
     RETURN
    0.27
    Activations Density 0.228%

    No Known Activations