© 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. 116563
    Prev
    Next
    INDEX
    Explanations

    wait, what, oh, oops

    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
    ản
    -0.09
     Needless
    -0.08
    isme
    -0.08
    ovsky
    -0.08
     hypert
    -0.08
     occupying
    -0.08
    (||
    -0.08
     supplied
    -0.08
    uilt
    -0.08
     practically
    -0.08
    POSITIVE LOGITS
     Oh
    0.38
     oh
    0.37
    Oh
    0.31
     Ah
    0.30
     Oops
    0.28
     OH
    0.27
    Ah
    0.27
     ah
    0.26
    oh
    0.26
    Oops
    0.25
    Activations Density 0.083%

    No Known Activations