© 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. 14545
    Prev
    Next
    INDEX
    Explanations

    north or south

    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
    out
    -0.08
    outs
    -0.08
    arse
    -0.08
    emos
    -0.08
    Ray
    -0.07
    912
    -0.07
    ccb
    -0.07
    -out
    -0.07
    zi
    -0.07
    IMO
    -0.07
    POSITIVE LOGITS
     purch
    0.10
    ạ
    0.10
    .ylabel
    0.10
     convinc
    0.09
     fax
    0.09
     famously
    0.09
    iesel
    0.09
     wcs
    0.09
     incredibly
    0.09
     collusion
    0.09
    Activations Density 0.955%

    No Known Activations