© 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. 18425
    Prev
    Next
    INDEX
    Explanations

    seeking ideas or solutions

    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
     Pit
    -0.11
     promise
    -0.11
     Carrier
    -0.10
    cascade
    -0.10
    idth
    -0.10
     Lan
    -0.09
    .Builder
    -0.09
    Haz
    -0.09
     promised
    -0.09
     Promise
    -0.09
    POSITIVE LOGITS
     altogether
    0.10
     notions
    0.10
     replay
    0.10
     ideas
    0.10
     instead
    0.09
     nett
    0.09
    qe
    0.09
     Idea
    0.08
    stead
    0.08
    Instead
    0.08
    Activations Density 0.005%

    No Known Activations