© 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. 14913
    Prev
    Next
    INDEX
    Explanations

    Archives followed by date

    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
     particulars
    -0.11
    ITA
    -0.11
    ottom
    -0.10
     Motor
    -0.10
    unde
    -0.10
     Arn
    -0.10
    ZO
    -0.10
     begs
    -0.10
    isman
    -0.09
    \R
    -0.09
    POSITIVE LOGITS
    enko
    0.09
    ÑĢем
    0.09
     tc
    0.09
    arel
    0.08
    -Identifier
    0.08
     truncated
    0.08
     Dixon
    0.08
     Richardson
    0.08
     Legends
    0.08
     Eh
    0.07
    Activations Density 0.013%

    No Known Activations