© 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. 46657
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    ibi
    -0.09
     Lots
    -0.09
    lots
    -0.09
     lots
    -0.08
    chs
    -0.08
    immel
    -0.08
    umas
    -0.08
    iya
    -0.08
    LAT
    -0.08
     footage
    -0.08
    POSITIVE LOGITS
    fold
    0.16
     different
    0.15
    -dollar
    0.14
    -fold
    0.13
    -times
    0.12
     times
    0.11
    -yard
    0.11
     Shades
    0.11
    ÂŃs
    0.11
    -plus
    0.11
    Activations Density 0.007%

    No Known Activations