© 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. 27877
    Prev
    Next
    INDEX
    Explanations

    going to / went / out

    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
    anca
    -0.14
     separation
    -0.12
     obr
    -0.11
    afia
    -0.11
    obl
    -0.11
     ydk
    -0.11
     oblivious
    -0.11
    ç¦
    -0.11
     Separ
    -0.11
     duly
    -0.10
    POSITIVE LOGITS
     shower
    0.12
     showers
    0.10
     Went
    0.10
     shopping
    0.10
     went
    0.09
     Shower
    0.09
     bath
    0.09
     temporary
    0.08
     Rent
    0.08
    åİ»
    0.08
    Activations Density 0.034%

    No Known Activations