© 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. 90281
    Prev
    Next
    INDEX
    Explanations

    titles and settings

    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
     Suff
    -0.08
     playful
    -0.08
     suff
    -0.08
     Bison
    -0.07
     Dav
    -0.07
     Rotary
    -0.07
     rand
    -0.06
     tav
    -0.06
     friendly
    -0.06
     triang
    -0.06
    POSITIVE LOGITS
     Chronicles
    0.15
    ocalypse
    0.13
     Trilogy
    0.13
     Wars
    0.12
    âĺĨ
    0.12
     starring
    0.12
     trilogy
    0.12
     reboot
    0.12
    rese
    0.11
    atoon
    0.11
    Activations Density 0.498%

    No Known Activations