© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117525
    Prev
    Next
    INDEX
    Explanations

    juicy descriptions

    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
    Negative Logits
    stad
    -0.12
     incap
    -0.10
     Bottle
    -0.09
    orca
    -0.09
     snow
    -0.09
    Cookie
    -0.09
     Clare
    -0.09
     Mixed
    -0.08
     tea
    -0.08
    plist
    -0.08
    POSITIVE LOGITS
     frags
    0.10
     Cout
    0.10
    ly
    0.10
     peach
    0.10
    æ¶
    0.10
    sse
    0.10
    -packed
    0.10
     chunks
    0.09
     gossip
    0.09
    /o
    0.09
    Activations Density 0.002%

    No Known Activations