© 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. 26331
    Prev
    Next
    INDEX
    Explanations

    good law / cause / pro se / mapping / registration / kick

    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
     wee
    -0.15
     bum
    -0.14
     dude
    -0.13
     Aussie
    -0.13
     lad
    -0.12
     dope
    -0.12
     eh
    -0.12
     fuck
    -0.12
     darn
    -0.12
     fucking
    -0.11
    POSITIVE LOGITS
    adt
    0.11
     Eis
    0.11
    aises
    0.11
    haps
    0.10
     effortless
    0.10
    apanese
    0.10
     trav
    0.10
     Gui
    0.10
    esco
    0.10
    ume
    0.10
    Activations Density 0.020%

    No Known Activations