© 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. 30278
    Prev
    Next
    INDEX
    Explanations

    profession or career highlights

    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
    -&
    -0.09
    emes
    -0.08
     Theatre
    -0.08
    styl
    -0.08
     sed
    -0.08
     Stadium
    -0.08
     binge
    -0.08
    illet
    -0.08
     Audience
    -0.08
     audience
    -0.08
    POSITIVE LOGITS
     recipro
    0.12
    alo
    0.12
     gubern
    0.11
    tea
    0.11
    Bookmark
    0.11
    tte
    0.11
    TTY
    0.10
    Interop
    0.10
     traveling
    0.10
     Pleasant
    0.10
    Activations Density 0.041%

    No Known Activations