© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113716
    Prev
    Next
    INDEX
    Explanations

    returning to places R locations

    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
     anymore
    -0.13
     beforehand
    -0.13
    rewrite
    -0.10
     Ir
    -0.10
     outright
    -0.10
    ini
    -0.10
     nearby
    -0.10
    ende
    -0.10
    ody
    -0.09
    azi
    -0.09
    POSITIVE LOGITS
     fray
    0.12
     resume
    0.11
     whence
    0.10
    weg
    0.10
     after
    0.10
    /original
    0.09
    iss
    0.09
     interrupted
    0.09
    logged
    0.09
     Resume
    0.09
    Activations Density 0.187%

    No Known Activations