© 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. 17062
    Prev
    Next
    INDEX
    Explanations

    tips on how to

    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
     Skinner
    -0.10
    ancell
    -0.09
     Pon
    -0.09
    angle
    -0.09
    zk
    -0.09
     inherently
    -0.09
    arin
    -0.09
    RP
    -0.09
    elon
    -0.09
     manip
    -0.09
    POSITIVE LOGITS
     :↵↵↵↵
    0.13
    :↵↵
    0.12
    :↵↵↵
    0.12
    ":↵↵
    0.11
     :↵↵
    0.10
    ):↵↵
    0.10
    ':↵↵
    0.10
    ():↵↵
    0.10
    :↵↵↵↵
    0.10
     fond
    0.10
    Activations Density 0.099%

    No Known Activations