© 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. 4637
    Prev
    Next
    INDEX
    Explanations

    the institution or the website

    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
     Pun
    -0.08
     sonic
    -0.08
    pte
    -0.08
    wy
    -0.08
    ws
    -0.08
     multiple
    -0.08
    eron
    -0.08
     hundreds
    -0.07
    omi
    -0.07
    ³
    -0.07
    POSITIVE LOGITS
     site
    0.16
     website
    0.16
     downside
    0.16
     company
    0.14
     drawback
    0.13
     platform
    0.11
    mina
    0.11
     lobby
    0.11
     interface
    0.11
     conced
    0.11
    Activations Density 0.006%

    No Known Activations