© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50660
    Prev
    Next
    INDEX
    Explanations

    ideal or perfect scenario

    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
    rob
    -0.11
    brands
    -0.09
    inho
    -0.09
     Tested
    -0.09
    viz
    -0.09
    eni
    -0.09
    bast
    -0.09
     inferior
    -0.09
    /vendor
    -0.09
     poor
    -0.09
    POSITIVE LOGITS
     ideal
    0.27
     Ideal
    0.24
    ideal
    0.22
    Ideal
    0.21
     ideally
    0.20
     Ideally
    0.16
     hypothetical
    0.15
     scenario
    0.15
     perfect
    0.14
     imagined
    0.14
    Activations Density 0.042%

    No Known Activations