© 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. 6342
    Prev
    Next
    INDEX
    Explanations

    if

    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
     sometimes
    -0.10
     seemingly
    -0.09
    zell
    -0.09
     forget
    -0.09
     dab
    -0.09
     yourself
    -0.08
     ull
    -0.08
     Barnett
    -0.08
     GOOD
    -0.08
     fog
    -0.08
    POSITIVE LOGITS
     indeed
    0.22
     truly
    0.19
    Indeed
    0.17
    inde
    0.16
     Indeed
    0.16
     genuinely
    0.14
     Truly
    0.14
     worst
    0.13
     true
    0.11
    true
    0.11
    Activations Density 0.120%

    No Known Activations