© 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. 17088
    Prev
    Next
    INDEX
    Explanations

    worse scenarios

    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
    oki
    -0.09
    peng
    -0.09
     :)↵
    -0.09
    éĸ
    -0.09
    assa
    -0.09
     :)↵↵
    -0.09
    owell
    -0.09
    Sessions
    -0.09
    095
    -0.08
    bv
    -0.08
    POSITIVE LOGITS
     worse
    1.03
     Worse
    0.94
     worst
    0.87
     Worst
    0.74
     wors
    0.50
    wor
    0.50
     worsening
    0.35
    orse
    0.31
    orst
    0.25
     weir
    0.23
    Activations Density 0.365%

    No Known Activations