© 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. 30966
    Prev
    Next
    INDEX
    Explanations

    py followed by re, crypt, ren, el, rim, ro, ru, or pyel

    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
     vids
    -0.11
     Fres
    -0.11
    leur
    -0.10
    887
    -0.10
    åĵģ
    -0.10
    wiki
    -0.10
     Kurd
    -0.10
     unh
    -0.10
     holland
    -0.10
    pers
    -0.10
    POSITIVE LOGITS
    eph
    0.09
    -earth
    0.09
     retard
    0.08
     trouble
    0.08
    erializer
    0.08
    esium
    0.08
     troubles
    0.08
    eners
    0.08
    esian
    0.08
    iq
    0.08
    Activations Density 0.013%

    No Known Activations