© 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. 17610
    Prev
    Next
    INDEX
    Explanations

    ...

    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
    pst
    -0.11
     Peg
    -0.10
    oad
    -0.09
    ilyn
    -0.09
     nomin
    -0.08
    /trunk
    -0.08
     assass
    -0.08
     Gates
    -0.08
     bree
    -0.08
    265
    -0.08
    POSITIVE LOGITS
    and
    0.11
     ...↵↵↵↵
    0.10
    oron
    0.10
     âĢ¦↵↵
    0.09
     and
    0.09
     ....↵↵
    0.09
    ãģĿãģĹãģ¦
    0.09
    erts
    0.09
     moy
    0.08
     .
    0.08
    Activations Density 0.054%

    No Known Activations