© 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. 29745
    Prev
    Next
    INDEX
    Explanations

    lists, poetic, preparations

    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
     spaghetti
    -0.12
    abr
    -0.10
     taped
    -0.10
    oks
    -0.10
     volunteered
    -0.10
     typically
    -0.10
    chw
    -0.09
     stripper
    -0.09
    'n
    -0.09
    åı°
    -0.09
    POSITIVE LOGITS
     cour
    0.11
     Ars
    0.11
     deco
    0.11
     prolong
    0.11
     progn
    0.10
     preparations
    0.10
     prelim
    0.10
    undry
    0.10
     charming
    0.10
     prepar
    0.09
    Activations Density 0.022%

    No Known Activations