© 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. 31773
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     Collapse
    -0.11
    ziel
    -0.11
     Reverse
    -0.10
     collapses
    -0.10
     revers
    -0.10
     nons
    -0.10
     Bau
    -0.10
     mav
    -0.10
    lege
    -0.10
     pu
    -0.09
    POSITIVE LOGITS
    /by
    0.11
     TBD
    0.08
    -by
    0.08
    SHARE
    0.08
     dil
    0.08
     ninety
    0.08
     Cer
    0.08
    Views
    0.08
     cent
    0.08
    ubar
    0.07
    Activations Density 0.014%

    No Known Activations