© 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. 32574
    Prev
    Next
    INDEX
    Explanations

    examples of specific contexts

    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
     compreh
    -0.12
    ilden
    -0.12
     Tee
    -0.11
    lah
    -0.11
    .—
    -0.11
    "—
    -0.11
     Wass
    -0.11
     pr
    -0.10
    ”—
    -0.10
    eneg
    -0.10
    POSITIVE LOGITS
     Kai
    0.08
     Pew
    0.08
     educ
    0.08
     Circus
    0.07
     jag
    0.07
     tal
    0.07
     Cycl
    0.07
    ycl
    0.07
    Swipe
    0.07
     unearth
    0.07
    Activations Density 0.027%

    No Known Activations