© 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. 31126
    Prev
    Next
    INDEX
    Explanations

    smirk, sitcom, .svg, McMahon, hallmark, quirky, smokers

    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
    OTT
    -0.09
     Burr
    -0.09
    orda
    -0.08
    keepers
    -0.08
    ena
    -0.08
    /me
    -0.08
    mass
    -0.08
    RTC
    -0.08
     Russo
    -0.08
    ifers
    -0.08
    POSITIVE LOGITS
    ed
    0.21
    ly
    0.14
    ing
    0.13
    worthy
    0.12
    edList
    0.12
     devil
    0.12
    adel
    0.11
    gle
    0.11
    devil
    0.11
     smirk
    0.11
    Activations Density 0.002%

    No Known Activations