© 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. 112888
    Prev
    Next
    INDEX
    Explanations

    other people's posts

    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
     Biography
    -0.11
    alink
    -0.11
     occas
    -0.10
    centers
    -0.10
     formally
    -0.10
     Lips
    -0.10
     incr
    -0.10
     arbit
    -0.10
    GEST
    -0.10
    /rec
    -0.10
    POSITIVE LOGITS
     posts
    0.31
     comments
    0.30
     postings
    0.29
     posting
    0.28
     posted
    0.28
     replies
    0.27
     commenter
    0.26
     thread
    0.25
     posters
    0.24
     comment
    0.24
    Activations Density 0.293%

    No Known Activations