© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32212
    Prev
    Next
    INDEX
    Explanations

    skip

    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
    meld
    -0.11
     caps
    -0.10
    ocale
    -0.10
    vale
    -0.10
    iban
    -0.10
    duk
    -0.10
     mysteries
    -0.10
     Myst
    -0.09
     Devils
    -0.09
     Buster
    -0.09
    POSITIVE LOGITS
     skip
    0.21
     skipping
    0.19
     skips
    0.18
     skipped
    0.17
     Skip
    0.17
     Skipping
    0.17
    Skip
    0.16
    Skipping
    0.16
    skip
    0.15
    .skip
    0.15
    Activations Density 0.082%

    No Known Activations