© 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. 117459
    Prev
    Next
    INDEX
    Explanations

    not always preceded by definite

    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
     ever
    -0.11
     never
    -0.10
     somehow
    -0.09
     EVER
    -0.09
     anytime
    -0.09
     nowhere
    -0.09
    -ever
    -0.09
    eo
    -0.09
    anything
    -0.09
     anywhere
    -0.08
    POSITIVE LOGITS
     easy
    0.12
     guarantee
    0.12
     obvious
    0.11
     predictable
    0.10
    /exp
    0.10
     agreeing
    0.10
    -success
    0.10
    depending
    0.10
     necessarily
    0.10
     depending
    0.10
    Activations Density 0.019%

    No Known Activations