© 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. 4767
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
     selfie
    -0.31
     emoji
    -0.28
     selfies
    -0.26
     https
    -0.25
    https
    -0.25
     Brexit
    -0.25
     emojis
    -0.25
    201
    -0.25
     STEM
    -0.25
     millennials
    -0.25
    POSITIVE LOGITS
    200
    0.26
     iPod
    0.24
     XHTML
    0.22
     weblog
    0.21
     AOL
    0.21
     DVD
    0.20
     Bush
    0.20
    DVD
    0.19
     Saddam
    0.17
     MTV
    0.17
    Activations Density 9.535%

    No Known Activations