© 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. 7243
    Prev
    Next
    INDEX
    Explanations

    to me that

    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
     Bugs
    -0.10
     realization
    -0.10
     Bracket
    -0.09
    ners
    -0.09
    iesel
    -0.09
     Wilkinson
    -0.09
     Ports
    -0.09
    azi
    -0.09
    ëħ
    -0.09
    mi
    -0.09
    POSITIVE LOGITS
     Buk
    0.09
     swirl
    0.09
    cko
    0.09
     Kob
    0.08
     evident
    0.08
    arend
    0.08
    .rs
    0.08
     plenty
    0.08
     straps
    0.08
    çķ
    0.08
    Activations Density 0.011%

    No Known Activations