© 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. 16873
    Prev
    Next
    INDEX
    Explanations

    past, future, recent

    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
     presently
    -0.12
     previously
    -0.09
     currently
    -0.09
     onstage
    -0.09
     Previously
    -0.08
     Gent
    -0.08
     candid
    -0.08
     therein
    -0.08
     Discord
    -0.08
    lev
    -0.08
    POSITIVE LOGITS
    lut
    0.12
    oux
    0.11
    bucks
    0.10
     bouquet
    0.10
    ç«ł
    0.09
    few
    0.09
     Brooke
    0.09
    HN
    0.09
    886
    0.09
     algumas
    0.09
    Activations Density 0.062%

    No Known Activations