© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5484
    Prev
    Next
    INDEX
    Explanations

    more [adjective] [noun]

    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
    aign
    -0.11
    (Seq
    -0.11
    gfx
    -0.11
     legitimately
    -0.11
    .Disclaimer
    -0.11
    ruk
    -0.11
     Worst
    -0.10
    umat
    -0.10
    .*↵↵
    -0.10
    )|(
    -0.10
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.15
     options
    0.11
     instead
    0.11
    åĪĻ
    0.10
     option
    0.09
     meanwhile
    0.09
     fare
    0.09
     altogether
    0.08
     still
    0.08
    instead
    0.08
    Activations Density 0.038%

    No Known Activations