© 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. 88485
    Prev
    Next
    INDEX
    Explanations

    professional player

    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
     lum
    -0.09
    Least
    -0.09
     prostitution
    -0.08
    uts
    -0.08
    imes
    -0.08
     professions
    -0.08
     crashing
    -0.08
    itos
    -0.08
     Attr
    -0.07
     emergency
    -0.07
    POSITIVE LOGITS
     courteous
    0.10
     cleanly
    0.10
     decl
    0.09
     Amateur
    0.09
    еÑģÑģ
    0.09
     etiquette
    0.09
    pu
    0.09
     demeanor
    0.09
     Guidance
    0.09
    [var
    0.09
    Activations Density 0.106%

    No Known Activations