© 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. 14224
    Prev
    Next
    INDEX
    Explanations

    html tag closures

    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
     Dane
    -0.12
     Concord
    -0.11
    ems
    -0.11
    etti
    -0.10
    edb
    -0.10
     predictable
    -0.10
    abel
    -0.10
    fad
    -0.10
    uel
    -0.09
    abl
    -0.09
    POSITIVE LOGITS
     fascinated
    0.08
     sk
    0.08
     whe
    0.08
     Nexus
    0.08
     fans
    0.07
     fascination
    0.07
     personally
    0.07
    enen
    0.07
    memo
    0.07
     reproductive
    0.07
    Activations Density 0.006%

    No Known Activations