© 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. 7382
    Prev
    Next
    INDEX
    Explanations

    Emma names

    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
     AOL
    -0.10
    .getInputStream
    -0.09
     Tennessee
    -0.09
     Cyrus
    -0.08
     gospel
    -0.08
     Chattanooga
    -0.08
     peppers
    -0.08
     APPLY
    -0.08
     Raz
    -0.08
     pew
    -0.08
    POSITIVE LOGITS
     Emma
    0.19
    Emma
    0.18
    emma
    0.16
     Boston
    0.14
     Celtics
    0.13
     Xavier
    0.13
    Boston
    0.13
     Frost
    0.13
     Massachusetts
    0.12
     frost
    0.12
    Activations Density 0.117%

    No Known Activations